CSS-LM

1
[{"sentiment": "USED-FOR", "sentence": "We introduce [[ Diagram Parse Graphs -LRB- DPG -RRB- ]] as our representation to model the << structure of diagrams >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The model is a << two-layer self-organizing neural network >> which combines broadly-tuned -LRB- muscular -RRB- proprioceptive and [[ -LRB- cartesian -RRB- visual information ]] to calculate -LRB- angular -RRB- motor commands for the initial part of the movement of a two-link arm .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Extensive experiments show that our << method >> works satisfactorily on challenging image data , which establishes a technical foundation for solving several computer vision problems , such as motion analysis and image restoration , using the [[ blur information ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we present a novel [[ approach ]] to learn the << deep video representation >> by exploring both local and holistic contexts .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We then extend the algorithm to model temporal smoothness in object shape , thus allowing [[ it ]] to handle severe cases of << missing data >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In such domains a [[ cascade of simple classifiers ]] each trained to achieve high detection rates and modest false positive rates can yield a final << detector >> with many desirable features : including high detection rates , very low false positive rates , and fast performance .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Ideally , [[ these ]] are basic vocabulary units suitable for different << tasks >> , such as speech and text understanding , machine translation , information retrieval , and statistical language modeling .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Layers in the input [[ images ]] will be mapped in the subspace , where it is proven that they form well-defined << clusters >> and can be reliably identified by a simple mean-shift based clustering algorithm .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Given a set of available source languages , we apply [[ language identification ]] to pick the language most similar to the target language , for more efficient use of << multilingual resources >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper presents a new << two-pass algorithm >> for Extra Large -LRB- more than 1M words -RRB- Vocabulary COntinuous Speech recognition based on the [[ Information Retrieval -LRB- ELVIRCOS -RRB- ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ Graphical models ]] such as Bayesian Networks -LRB- BNs -RRB- are being increasingly applied to various << computer vision problems >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Two themes have evolved in speech and text image processing work at Xerox PARC that expand and redefine the role of [[ recognition technology ]] in << document-oriented applications >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< It >> is used for the synthesis method based on a [[ selection of articulatory targets ]] and interpolation technique .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We discuss [[ maximum a posteriori estimation ]] of << continuous density hidden Markov models -LRB- CDHMM -RRB- >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Other tasks using the [[ method ]] developed for << ILIMP >> are described briefly , as well as the use of ILIMP in a modular syntactic analysis system .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ HBG ]] incorporates lexical , syntactic , semantic , and structural information from the parse tree into the << disambiguation process >> in a novel way .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We describe a novel technique and implemented << system >> for constructing a subcategorization dictionary from [[ textual corpora ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The connectionist component is trained either from << patterns >> derived from the [[ rules of a deterministic grammar ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , a new << mechanism >> , based on the concept of sublanguage , is proposed for identifying unknown words , especially personal names , in [[ Chinese newspapers ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper discusses a method of << analyzing metaphors >> based on the existence of a small number of [[ generalized metaphor mappings ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Although << non-linear extensions of active shape models >> have been proposed and application specific solutions have been used , they still need a certain amount of [[ user interaction ]] during model building .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "After introducing this [[ approach ]] to << MT system design >> , and the basics of monolingual UCG , we will show how the two can be integrated , and present an example from an implemented bi-directional English-Spanish fragment .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We argue in favor of the the use of labeled directed graph to represent various types of linguistic structures , and illustrate how [[ this ]] allows one to view << NLP tasks >> as graph transformations .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "It is achieved by deriving the [[ inter-sensor data ratio model ]] of an << AVS >> in bispectrum domain -LRB- BISDR -RRB- and exploring the favorable properties of bispectrum , such as zero value of Gaussian process and different distribution of speech and NSI .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The differential spectral feature is directly estimated using a << differential Gaussian mixture model -LRB- GMM -RRB- >> that is analytically derived from the traditional [[ GMM ]] used as a conversion model in the conventional SVC .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We propose an efficient [[ dialogue management ]] for an << information navigation system >> based on a document knowledge base .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << system >> is implemented in [[ CommonLisp ]] and has been tested on examples from German derivation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper a new LPC vocoder is presented which splits the << LPC excitation >> into two frequency bands using a [[ variable cutoff frequency ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "However , for << high-dimensional continuous-state tasks >> , it can be extremely difficult to build an accurate [[ model ]] , and thus often the algorithm returns a policy that works in simulation but not in real-life .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we evaluate the application of these [[ segmen-tation algorithms ]] to << large vocabulary speech recognition >> using statistical n-gram language models based on the proposed word segments instead of entire words .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << PDTB >> is being built directly on top of the [[ Penn TreeBank ]] and Propbank , thus supporting the extraction of useful syntactic and semantic features and providing a richer substrate for the development and evaluation of practical algorithms .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << model >> learns to automatically make these assignments based on a [[ discriminative training criterion ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We train our models on a dataset of urban aerial imagery consisting of ` same ' and ` different ' pairs , collected for this purpose , and characterize the << problem >> via a [[ human study ]] with annotations from Amazon Mechanical Turk .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We evaluate the performance of the << algorithm >> using [[ synthetic and real data ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We present a novel [[ weakly supervised algorithm ]] that can detect << behaviours >> that either have never before been seen or for which there are few examples .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes the [[ Hierarchical Directed Acyclic Graph -LRB- HDAG -RRB- Kernel ]] for << structured natural language data >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A tensor method tuned with carefully optimized derivative filters yields reliable and dense displacement vector fields -LRB- DVF -RRB- with an accuracy of up to a few hundredth << pixels/frame >> for [[ real-world images ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Four problems render vector space model -LRB- VSM -RRB- - based text classification approach ineffective : 1 -RRB- Many words within song lyrics actually contribute little to sentiment ; 2 -RRB- Nouns and verbs used to express sentiment are ambiguous ; 3 -RRB- Negations and [[ modifiers ]] around the sentiment keywords make particular contributions to << sentiment >> ; 4 -RRB- Song lyric is usually very short .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper we describe a novel [[ data structure ]] for phrase-based statistical machine translation which allows for the << retrieval of arbitrarily long phrases >> while simultaneously using less memory than is required by current decoder implementations .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Experimental results show that our method has permitted autonomous , stable and effective information integration to construct the [[ internal model ]] of << hierarchical perceptual sounds >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In addition , the [[ system ]] is adapted to a small set of football announcements , in an exploratory attempt to synthe-sise << expressive speech >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Such << knowledge >> comes either from domain experts based on their experience or from various [[ physical or geometric constraints ]] that govern the objects we try to model .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The combination with a << two-step clustering process >> using [[ sentence co-occurrences ]] as features allows for accurate results .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A [[ method ]] of << sense resolution >> is proposed that is based on WordNet , an on-line lexical database that incorporates semantic relations -LRB- synonymy , antonymy , hyponymy , meronymy , causal and troponymic entailment -RRB- as labeled pointers between word senses .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< HBG >> incorporates [[ lexical , syntactic , semantic , and structural information ]] from the parse tree into the disambiguation process in a novel way .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Furthermore , we present a [[ standalone system ]] that resolves pronouns in << unannotated text >> by using a fully automatic sequence of preprocessing modules that mimics the manual annotation process .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To advance research on animated GIF understanding , we collected a new dataset , Tumblr GIF -LRB- TGIF -RRB- , with 100K animated GIFs from Tumblr and 120K << natural language descriptions >> obtained via [[ crowdsourcing ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This [[ method ]] can be used in << applications >> such as information retrieval , routing , and text summarization .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Extensive experiments show that our [[ method ]] works satisfactorily on challenging image data , which establishes a technical foundation for solving several << computer vision problems >> , such as motion analysis and image restoration , using the blur information .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We also show that << SHORTSTR2 >> can be combined with a simple algorithm to identify short supports from [[ full-length supports ]] , to provide a superior drop-in replacement for STR2 + .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Although the experiments in this article are on natural language parsing -LRB- NLP -RRB- , the approach should be applicable to many other << NLP problems >> which are naturally framed as [[ ranking tasks ]] , for example , speech recognition , machine translation , or natural language generation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our experiment result shows that the [[ neural network ]] can learn a << language model >> that has performance even better than standard statistical methods .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We experimentally investigate the functioning of Ant-Q and we show that the results obtained by Ant-Q on symmetric TSP 's are competitive with those obtained by other << heuristic approaches >> based on neural networks or [[ local search ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In [[ Mimo ]] , the << translation of anaphoric relations >> is compositional .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our << approach >> is fully unsupervised and trained in an [[ end-to-end deep convolutional neu-ral network architecture ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "It is argued that the [[ method ]] reduces << metaphor interpretation >> from a reconstruction to a recognition task .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The objective is a generic [[ system ]] of tools , including a core English lexicon , grammar , and concept representations , for building << natural language processing -LRB- NLP -RRB- systems >> for text understanding .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we present a [[ corpus-based supervised word sense disambiguation -LRB- WSD -RRB- system ]] for << Dutch >> which combines statistical classification -LRB- maximum entropy -RRB- with linguistic information .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We show that the suggested << hybrid proba-bilistic model >> -LRB- which combines [[ global variables ]] , like translation , with local variables , like relative positions and appearances of body parts -RRB- , leads to : -LRB- i -RRB- faster convergence of learning phase , -LRB- ii -RRB- robustness to occlusions , and , -LRB- iii -RRB- higher recognition rate .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This [[ system ]] identifies << features >> of sentences based on semantic similarity measures and discourse structure .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We present a [[ syntax-based constraint ]] for << word alignment >> , known as the cohesion constraint .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We further show the usefulness of dormant independencies in model testing and induction by giving an [[ algorithm ]] that uses constraints entailed by dormant independencies to prune << extraneous edges >> from a given causal graph .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We propose a [[ detection method ]] for << orthographic variants >> caused by transliteration in a large corpus .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We propose and analyze a [[ block minimization framework ]] for << data >> larger than the memory size .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< MINPATH >> finds shortcuts by using a learned [[ model ]] of web visitor behavior to estimate the savings of shortcut links , and suggests only the few best links .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The algorithm operates on underspecified chart representations which are derived from dominance graphs ; it can be applied to the << USRs >> computed by [[ large-scale grammars ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we study the problem of diagram interpretation and reasoning , the challenging [[ task ]] of identifying the << structure of a diagram >> and the semantics of its constituents and their relationships .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We study and compare two novel [[ embedding methods ]] for << segmenting feature points of piece-wise planar structures >> from two -LRB- uncalibrated -RRB- perspective images .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Given a single modal low-resolution face image , we benefit from the [[ multiple factor interactions of training tensor ]] , and super-resolve its << high-resolution reconstructions >> across different modalities for face recognition .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Combining [[ speech recognition ]] and natural language processing to achieve << speech understanding >> , the system will be demonstrated in an application domain relevant to the DoD .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our results show the significance of our << models >> for syntactic parsing and question answering in diagrams using [[ DPGs ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "First , instead of using the model space as a regular-izer , we directly use [[ it ]] as our << search space >> , thus resulting in a more elegant formulation with fewer unknowns and fewer equations .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Ant-Q algorithms were inspired by work on the ant system -LRB- AS -RRB- , a [[ distributed algorithm ]] for << combinatorial optimization >> based on the metaphor of ant colonies which was recently proposed in -LRB- Dorigo , 1992 ; Dorigo , Maniezzo and Colorni , 1996 -RRB- .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "After an overview of our approach , we present results from experiments with << spelling correction >> in [[ Turkish ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Fortunately , an [[ intermediate domain ]] could often be found to build a bridge across them to facilitate the << learning problem >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "For each correspondence , instead of hard-mapping it to a single transformation , the << method >> augments its description by using [[ multiple dithered transformations ]] that are deterministically generated by the other correspondences .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Qualitative results show that our [[ method ]] captures information that is temporally varying , such as << human pose >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< It >> was compiled from various resources such as encyclopedias and dictionaries , [[ public databases of proper names and toponyms ]] , collocations obtained from Czech WordNet , lists of botanical and zoological terms and others .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "When a very noisy portion is detected , the << parser >> skips that portion using a fake [[ non-terminal symbol ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We describe an implementation of << data-driven selection >> of [[ emphatic facial displays ]] for an embodied conversational agent in a dialogue system .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Recently , [[ Stacked Auto-Encoders -LRB- SAE -RRB- ]] have been successfully used for << learning imbalanced datasets >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We show that this << task >> can be done using [[ bilingual parallel corpora ]] , a much more commonly available resource .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes that << sentence analysis >> should be treated as [[ defeasible reasoning ]] , and presents such a treatment for Japanese sentence analyses using an argumentation system by Konolige , which is a formalization of defeasible reasoning , that includes arguments and defeat rules that capture defeasibility .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We use an iterative procedure which alternates between clustering and training discriminative classifiers , while applying careful [[ cross-validation ]] at each step to prevent << overfitting >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We pursue a hierarchical sparse coding approach that learns features useful in discriminating images across locations , by initializing << it >> with a [[ geometric prior ]] corresponding to transformations between image appearance space and their corresponding location grouping space using the notion of parallel transport on manifolds .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< It >> was compiled from various resources such as encyclopedias and dictionaries , public databases of proper names and toponyms , collocations obtained from Czech WordNet , [[ lists of botanical and zoological terms ]] and others .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "For categorization task , positive feature vectors and [[ negative feature vectors ]] are used cooperatively to construct << generic , indicative summaries >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ Representing images with layers ]] has many important << applications >> , such as video compression , motion analysis , and 3D scene analysis .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We develop a new model , << TSI-pLSA >> , which extends [[ pLSA ]] -LRB- as applied to visual words -RRB- to include spatial information in a translation and scale invariant manner .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Then , an improved [[ SVM like learning system ]] incorporating the hypergraph regularization , called Rank-HLapSVM , is proposed to handle the << multi-label classification problems >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In particular , we explore the capacity and limitations of << statistical learning mechanisms >> that have recently gained prominence in [[ cognitive psychology ]] and linguistics .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The prior is given by a [[ kernel density estimate ]] on the space of << joint intensity distributions >> computed from a representative set of pre-registered image pairs .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "As a case study , we apply the [[ model ]] to << parse reranking >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we propose a more principled [[ way ]] to identify annotation outliers by formulating the interestingness prediction task as a unified robust learning to rank problem , tackling both the outlier detection and << interestingness prediction tasks >> jointly .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In doing so the [[ coder ]] 's performance during both mixed voicing speech and speech containing acoustic noise is greatly improved , producing << soft natural sounding speech >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Johnston 1998 presents an approach in which strategies for << multimodal integration >> are stated declaratively using a [[ unification-based grammar ]] that is used by a multidimensional chart parser to compose inputs .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This process enables the [[ system ]] to understand << user utterances >> based on the context of a dialogue .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper describes a particular << approach >> to parsing that utilizes recent advances in [[ unification-based parsing ]] and in classification-based knowledge representation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< Inference >> is based on [[ Markov chain Monte Carlo ]] , augmented with specific methods for generating efficient proposals when the domain contains many objects .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << SPR >> uses [[ ranking rules ]] automatically learned from training data .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper we formulate << story link detection >> and new event detection as [[ information retrieval task ]] and hypothesize on the impact of precision and recall on both systems .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We propose several sketching strategies , present a new [[ quasi-Newton method ]] that uses stochastic block BFGS updates combined with the variance reduction approach SVRG to compute << batch stochastic gradients >> , and prove linear convergence of the resulting method .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper a novel [[ solution ]] to << automatic and unsupervised word sense induction -LRB- WSI -RRB- >> is introduced .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The prior is given by a kernel density estimate on the space of << joint intensity distributions >> computed from a representative set of [[ pre-registered image pairs ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Experiments on connected-digit recognition show that when using explicit duration constraints the [[ decoder ]] generates << word matches >> with more reasonable durations , and word error rates are significantly reduced across a broad range of noise conditions .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our logical definition leads to a neat relation to categorial grammar , -LRB- yielding a treatment of Montague semantics -RRB- , a parsing-as-deduction in a resource sensitive logic , and a << learning algorithm >> from structured data -LRB- based on a typing-algorithm and [[ type-unification ]] -RRB- .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Each of these [[ parsing strategies ]] exploits different types of knowledge ; and their combination provides a strong framework in which to process conjunctions , << fragmentary input >> , and ungrammatical structures , as well as less exotic , grammatically correct input .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The data from those recordings was used in a range of [[ models ]] for generating << facial displays >> , each model making use of a different amount of context or choosing displays differently within a context .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The result of the comparison was that the dictionary-based word vectors better reflect taxonomic similarity , while the [[ LSA-based and the cooccurrence-based word vectors ]] better reflect << associative similarity >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes an [[ approach ]] to << full parsing >> suitable for Information Extraction from texts .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper addresses the issue of word-sense ambiguity in extraction from [[ machine-readable resources ]] for the << construction of large-scale knowledge sources >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The paper presents a << method >> for word sense disambiguation based on [[ parallel corpora ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We primarily focus on the description of the << syntactically motivated relations in discourse >> , basing our findings on the theoretical background of the Prague Dependency Treebank 2.0 and the [[ Penn Discourse Treebank 2 ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The key idea is to successively `` ground '' the << policy evaluations >> using [[ real-life trials ]] , but to rely on the approximate model to suggest local changes .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We show some applications of this << solution >> to additional temporal anaphora phenomena in [[ quantified sentences ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Based on the model , a [[ music scene analysis system ]] has been developed for acoustic signals of ensemble music , which recognizes rhythm , chords , and << source-separated musical notes >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ Existing methods ]] for << supervised dimensionality reduction >> often presume that the data is densely sampled so that a neighborhood graph structure can be formed , or that the data arises from a known distribution .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We propose a Bayesian semi-supervised Chinese word segmentation model which uses both monolingual and bilingual information to derive a [[ segmentation ]] suitable for << MT >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "By those assumptions we cast the problem as a [[ Quadratic Eigenvalue Problem ]] offering an elegant way of treating nonlinear monomials and delivering a << quasi closed-form solution >> as a reliable starting point for a further bundle adjustment .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We demonstrate that an [[ approximation of HPSG ]] produces a more effective << CFG filter >> than that of LTAG .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our [[ system ]] is suitable for << embedded computer vision application >> based on three reasons .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We trained classifiers on the speech processes extracted from the << alignments >> of an APT and an MPT with a [[ canonical transcription ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks : -LRB- 1 -RRB- for << predicting subtopic boundaries >> , the [[ lexical cohesion-based approach ]] alone can achieve competitive results , -LRB- 2 -RRB- for predicting top-level boundaries , the machine learning approach that combines lexical-cohesion and conversational features performs best , and -LRB- 3 -RRB- conversational cues , such as cue phrases and overlapping speech , are better indicators for the top-level prediction task .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Using [[ pairwise constraints ]] for << ensemble construction >> is challenging because it remains unknown how to influence the base classifiers with the sampled pairwise constraints .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Because of its adaptive nature , [[ Bayesian learning ]] serves as a unified approach for the following four << speech recognition applications >> , namely parameter smoothing , speaker adaptation , speaker group modeling and corrective training .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We propose a method that automatically generates [[ paraphrase ]] sets from seed sentences to be used as reference sets in objective << machine translation evaluation measures >> like BLEU and NIST .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Also , we provide an advanced << method >> to acquire generalized translation knowledge using the extracted [[ paraphrases ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper addresses the issue of << word-sense ambiguity >> in extraction from [[ machine-readable resources ]] for the construction of large-scale knowledge sources .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The maximum eigenvalue of the tensor is used to construct a [[ Finite Time Lyapunov Exponent -LRB- FTLE -RRB- field ]] , which reveals the << Lagrangian Coherent Structures -LRB- LCS -RRB- >> present in the underlying flow .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We use this [[ geometric understanding of conjugate priors ]] to derive the << hyperparameters >> and expression of the prior used to couple the generative and discriminative components of a hybrid model for semi-supervised learning .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The experimental results show that SRDA works well on recognition and classification , implying that [[ semi-Riemannian geometry ]] is a promising new tool for pattern recognition and << machine learning >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The results demonstrates that the classifier based on SAE detects the << ASR errors >> better than the other [[ classification methods ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We describe a new approach which involves << clustering subcategorization frame -LRB- SCF -RRB- distributions >> using the [[ Information Bottleneck and nearest neighbour methods ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we compare the performance of a state-of-the-art statistical parser -LRB- Bikel , 2004 -RRB- in parsing written and spoken language and in << generating sub-categorization cues >> from [[ written and spoken language ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The objective of this project is to develop a << robust and high-performance speech recognition system >> using a segment-based approach to [[ phonetic recognition ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We describe the use of text data scraped from the web to augment [[ language models ]] for << Automatic Speech Recognition >> and Keyword Search for Low Resource Languages .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << method >> exploits recent advances in word alignment and word clustering based on [[ automatic extraction of translation equivalents ]] and being supported by available aligned wordnets for the languages in the corpus .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We solve the three << factors >> in a [[ coarse-to-fine manner ]] and achieve reliable change decision by rank minimization .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our [[ approach ]] is suitable for << urban and indoor environments >> where most lines are either parallel or orthogonal to each other .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We conduct experimental evaluations and show that << real-time VC >> is capable of running on a [[ DSP ]] with little degradation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In our method , [[ unsupervised training ]] is first used to train a phone n-gram model for a particular << domain >> ; the output of recognition with this model is then passed to a phone-string classifier .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ TUIT ]] is a software library that can be used to construct << multilingual TIPSTER user interfaces >> for a set of common user tasks .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In particular , we explore the capacity and limitations of << statistical learning mechanisms >> that have recently gained prominence in cognitive psychology and [[ linguistics ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In our method , the estimate of the inverse Hessian matrix that is maintained by << it >> , is updated at each iteration using a sketch of the [[ Hessian ]] , i.e. , a randomly generated compressed form of the Hessian .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The idea behind our << method >> is to utilize certain layout structures and [[ linguistic pattern ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We fit each incomplete scan using << template fitting techniques >> with a generic [[ human template ]] , and register all scans to every pose using global consistency constraints .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In the phase of annotation , for an unlabeled image , the most likely associated << keywords >> are predicted in terms of the [[ blob-token set ]] extracted from the given image .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We show experimental results on << block selection criteria >> based on [[ unigram counts ]] and phrase length .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< Finegrained CFG rules >> are automatically induced from a [[ parsed corpus ]] by training a PCFG-LA model using an EM-algorithm .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ Photometric processing ]] serves the double purpose of increasing the amount of << recovered surface detail >> and of enabling the structured-light setup to be robustly self-calibrated .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This [[ approach ]] differs from other approaches to << WSI >> in that it enhances the effect of the one sense per collocation observation by using triplets of words instead of pairs .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The other extreme , << model-free RL >> , tends to require infeasibly large numbers of [[ real-life trials ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We conclude by showing how our [[ design ]] can provide a rich and robust information base to a << language assessment / correction application >> by modeling user proficiency at a high level of granularity and specificity .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "It is general , i.e. , it can be used to minimize any << energy function >> -LRB- e.g. , unary , pairwise , and higher-order terms -RRB- with any existing [[ energy minimization algorithm ]] -LRB- e.g. , graph cuts and belief propagation -RRB- .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper examines the properties of << feature-based partial descriptions >> built on top of [[ Halliday 's systemic networks ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes that sentence analysis should be treated as defeasible reasoning , and presents such a [[ treatment ]] for << Japanese sentence analyses >> using an argumentation system by Konolige , which is a formalization of defeasible reasoning , that includes arguments and defeat rules that capture defeasibility .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To validate our method , we compare << it >> with the Maximum Likelihood -LRB- ML -RRB- estimation method under sparse data and with the Expectation Maximization -LRB- EM -RRB- algorithm under [[ incomplete data ]] respectively .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The proposed << technique >> operates on [[ syntactically shallow-parsed corpora ]] on the basis of a limited number of search heuristics not relying on any previous lexico-syntactic knowledge about SCFs .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The model is a << pushdown automaton >> augmented with the ability to check reduplication by using the [[ stack ]] in a new way .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we present a novel << approach >> to learn the deep video representation by exploring both [[ local and holistic contexts ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "MINPATH finds shortcuts by using a learned [[ model ]] of web visitor behavior to estimate the << savings of shortcut links >> , and suggests only the few best links .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << stemming model >> is based on [[ statistical machine translation ]] and it uses an English stemmer and a small -LRB- 10K sentences -RRB- parallel corpus as its sole training resources .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Although the system performs well within a limited textual domain , further research is needed to make [[ it ]] effective for << open-domain question answering >> and text summarisation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The operations are reduced to functions of a formal language , thus changing the level of abstraction of the [[ operations ]] to be performed on << SI-Nets >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes a << two-phase shift-reduce dependency parser >> based on [[ SVM learning ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Using the results of the [[ statistical analysis ]] , we propose an << algorithm >> for lower bound estimation for Named Entity corpora and discuss the significance of the cross-lingual comparisons provided by the analysis .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We present a << method >> for detecting 3D objects using [[ multi-modalities ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "These experiments were dual purpose : -LRB- 1 -RRB- to validate the central thesis of the work of -LRB- Levin , 1993 -RRB- , i.e. , that verb semantics and syntactic behavior are predictably related ; -LRB- 2 -RRB- to demonstrate that a 15-fold improvement can be achieved in deriving << semantic information >> from [[ syntactic cues ]] if we first divide the syntactic cues into distinct groupings that correlate with different word senses .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we focus on the minimal labeling problem -LRB- MLP -RRB- and we propose an [[ algorithm ]] to efficiently derive all the feasible base relations of a << QCN >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We show how research in generation can be adapted to dialog systems , and how the high cost of << hand-crafting knowledge-based generation systems >> can be overcome by employing [[ machine learning techniques ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper we present << SHORTSTR2 >> , a development of the [[ Simple Tabular Reduction algorithm STR2 + ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< It >> was compiled from various resources such as encyclopedias and [[ dictionaries ]] , public databases of proper names and toponyms , collocations obtained from Czech WordNet , lists of botanical and zoological terms and others .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The proposed algorithm is based on a [[ statistical model of short-term log-energy sequences ]] for << echo-free speech >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we cast the problem of << point cloud matching >> as a [[ shape matching problem ]] by transforming each of the given point clouds into a shape representation called the Schr\u00f6dinger distance transform -LRB- SDT -RRB- representation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The recognizer makes use of [[ continuous density HMM ]] with Gaussian mixture for << acoustic modeling >> and n-gram statistics estimated on the newspaper texts for language modeling .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A pilot system for extracting these << relations >> automatically from an ordinary [[ Japanese language dictionary ]] -LRB- Shinmeikai Kokugojiten , published by Sansei-do , in machine readable form -RRB- is given .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our << acquisition program - LEXICALL - >> takes , as input , the result of previous work on [[ verb classification ]] and thematic grid tagging , and outputs LCS representations for different languages .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "One of the major scientific goals of [[ SmartKom ]] is to design new << computational methods >> for the seamless integration and mutual disambiguation of multimodal input and output on a semantic and pragmatic level .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The stemming model is based on statistical machine translation and << it >> uses an [[ English stemmer ]] and a small -LRB- 10K sentences -RRB- parallel corpus as its sole training resources .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The [[ method ]] outperforms its state-of-the-art counterparts in both accuracy and scalability , especially when it comes to the << retrieval of small , rotated objects >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A novel [[ cluster tree ]] enforces << sequential tracking in local segments >> of the sequence while allowing global non-sequential traversal among these segments .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Inference in these models involves solving a << combinatorial optimization problem >> , with [[ methods ]] such as graph cuts , belief propagation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Thereby a << system of relevant times >> provided by the preceeding text and by the [[ temporal adverbials ]] of the sentence being processed is used .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we compare the performance of a state-of-the-art [[ statistical parser ]] -LRB- Bikel , 2004 -RRB- in << parsing written and spoken language >> and in generating sub-categorization cues from written and spoken language .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper presents an [[ approach ]] to the << unsupervised learning of parts of speech >> which uses both morphological and syntactic information .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A new [[ exemplar-based framework ]] unifying image completion , << texture synthesis >> and image inpainting is presented in this work .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This study presents a method to automatically acquire paraphrases using bilingual corpora , which utilizes the << bilingual dependency relations >> obtained by projecting a [[ monolingual dependency parse ]] onto the other language sentence based on statistical alignment techniques .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The experimental results show that [[ SRDA ]] works well on << recognition >> and classification , implying that semi-Riemannian geometry is a promising new tool for pattern recognition and machine learning .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Finally , we analyze the experimental results and propose [[ normative principles ]] for << background maintenance >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We show how the resulting << optimization problem >> can be reduced to an equivalent [[ convex problem ]] with a small number of constraints , and solve it using an efficient scheme .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Then , we build the << base clas-sifiers >> with the new [[ data representation ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< Syntax-based statistical machine translation -LRB- MT -RRB- >> aims at applying [[ statistical models ]] to structured data .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To further scale beyond this dataset , we propose a [[ semi-supervised learning framework ]] to expand the pool of << labeled data >> with high confidence predictions obtained from unlabeled data .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The framework of the << analysis >> is [[ model-theoretic semantics ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Since it is unlikely that there exists a polynomial time solution for any of these hard problems -LRB- unless P = NP and P #P = P -RRB- , our results highlight and justify the need for developing [[ polynomial time approximations ]] for these << computations >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ PAKTUS ]] supports the adaptation of the generic core to a variety of domains : << JINTACCS messages >> , RAINFORM messages , news reports about a specific type of event , such as financial transfers or terrorist acts , etc. , by acquiring sublanguage and domain-specific grammar , words , conceptual mappings , and discourse patterns .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The parser computes a compact [[ parse forest representation ]] of the complete set of possible analyses for << large treebank grammars >> and long input sentences .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes a novel [[ method ]] of << building polarity-tagged corpus >> from HTML documents .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our aim is to revisit the present-day syntactico-semantic -LRB- tectogrammatical -RRB- annotation in the Prague Dependency Treebank , extend [[ it ]] for the purposes of a << sentence-boundary-crossing representation >> and eventually to design a new , discourse level of annotation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The [[ system ]] also has several choices in << generating responses or confirmations >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Unlike evaluations in the SRE series , the << i-vector challenge >> was run entirely online and used fixed-length feature vectors projected into a [[ low-dimensional space -LRB- i-vectors -RRB- ]] rather than audio recordings .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This approach differs from other [[ approaches ]] to << WSI >> in that it enhances the effect of the one sense per collocation observation by using triplets of words instead of pairs .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We also show that [[ SHORTSTR2 ]] can be combined with a simple algorithm to identify << short supports >> from full-length supports , to provide a superior drop-in replacement for STR2 + .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Finally , we combine MHI and HMHH together and extract a [[ low dimension feature vector ]] to be used in the << SVM classifiers >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Experiments on [[ connected-digit recognition ]] show that when using explicit duration constraints the << decoder >> generates word matches with more reasonable durations , and word error rates are significantly reduced across a broad range of noise conditions .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We also propose exploiting the [[ non-uniformity ]] of a Hough histogram as the spatial similarity to handle << multiple matching surfaces >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "It was discovered recently , that exploiting the << sparsity of sources >> in an appropriate representation according to some [[ signal dictionary ]] , dramatically improves the quality of separation .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To overcome this limitation , we propose a novel [[ mapping algorithm ]] that derives the << relative positioning >> and orientation between two PTZ cameras based on a unified polynomial model .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The mapping between the data and the hidden space is nonlinear , so we use an [[ approximate variational technique ]] for inference and << learning >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The information gained from corpus research and the analyses that are proposed are realized in the framework of << SILVA >> , a parsing and extraction tool for [[ German text corpora ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A [[ genetic algorithm ]] guides the novel facades as well as << inpainted parts >> to be consistent with the example , both in terms of their overall structure and their detailed textures .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper we show how to support << full unification >> in these [[ algorithms ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , a novel [[ method ]] to learn the << intrinsic object structure >> for robust visual tracking is proposed .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "First , a very simple , << randomized sentence-plan-generator -LRB- SPG -RRB- >> generates a potentially large list of possible sentence plans for a given [[ text-plan input ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper describes to what extent << deep processing >> may benefit from [[ shallow techniques ]] and it presents a NLP system which integrates a linguistic PoS tagger and chunker as a preprocessing module of a broad coverage unification based grammar of Spanish .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "CRL developed [[ TUIT ]] to support their work to integrate << TIPSTER modules >> for the 6 and 12 month TIPSTER II demonstrations as well as their Oleada and Temple demonstration projects .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper presents an << evaluation method >> employing a [[ latent variable model ]] for paraphrases with their contexts .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The [[ recognition system ]] will eventually be integrated with natural language processing to achieve << spoken language understanding >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "One is << string similarity >> based on [[ edit distance ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Electrolaryngeal speech is one of the typical types of alaryngeal speech produced by an alternative [[ speaking method ]] for << laryngectomees >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We use a maximum likelihood criterion to train a << log-linear block bigram model >> which uses [[ real-valued features ]] -LRB- e.g. a language model score -RRB- as well as binary features based on the block identities themselves , e.g. block bigram features .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A central problem of word sense disambiguation -LRB- WSD -RRB- is the lack of [[ manually sense-tagged data ]] required for << supervised learning >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To validate our method , we compare << it >> with the Maximum Likelihood -LRB- ML -RRB- estimation method under [[ sparse data ]] and with the Expectation Maximization -LRB- EM -RRB- algorithm under incomplete data respectively .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We present an efficient algorithm for the redundancy elimination problem : Given an underspecified semantic representation -LRB- USR -RRB- of a scope ambiguity , compute an << USR >> with fewer mutually [[ equivalent readings ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Then we propose a novel [[ data mining method ]] to efficiently discover the << optimal co-occurrence pattern >> with minimum empirical error , despite the noisy training dataset .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper presents an [[ approach ]] to estimate the << intrinsic texture properties -LRB- albedo , shading , normal -RRB- of scenes >> from multiple view acquisition under unknown illumination conditions .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << parser >> uses [[ bit-vector operations ]] to parallelise the basic parsing operations .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To further demonstrate its applications for computer vision , we apply it to learn a BN model for << facial Action Unit -LRB- AU -RRB- recognition >> from [[ real image data ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This study compares the effect of noise and reverberation on << depression prediction >> using 1 -RRB- standard [[ mel-frequency cepstral coefficients -LRB- MFCCs -RRB- ]] , and 2 -RRB- features designed for noise robustness , damped oscillator cepstral coefficients -LRB- DOCCs -RRB- .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Using linearly interpolated language models , we find that blogs and [[ movie subtitles ]] are more relevant for << language modeling of conversational telephone speech >> and obtain large reductions in out-of-vocabulary keywords .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In contrast to existing << methods >> that consider only the [[ guidance image ]] , our method can selectively transfer salient structures that are consistent in both guidance and target images .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The << method >> exploits recent advances in word alignment and word clustering based on automatic extraction of translation equivalents and being supported by available [[ aligned wordnets ]] for the languages in the corpus .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper presents a simple way to incorporate << word duration constraints >> by [[ unrolling HMMs ]] to form a lattice where word duration probabilities can be applied directly to state transitions .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper describes a [[ system ]] -LRB- RAREAS -RRB- which synthesizes << marine weather forecasts >> directly from formatted weather data .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The paper presents a [[ method ]] for << word sense disambiguation >> based on parallel corpora .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Or , -LRB- 2 -RRB- the context of the polysemous word will be used as a key to search a large corpus ; all words found to occur in that context will be noted ; WordNet will then be used to estimate the semantic distance from those words to the alternative senses of the polysemous word ; and that sense will be chosen that is closest in meaning to other words occurring in the same context If successful , this [[ procedure ]] could have practical applications to problems of << information retrieval >> , mechanical translation , intelligent tutoring systems , and elsewhere .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes [[ document oriented preference sets -LRB- DoPS -RRB- ]] for the << disambiguation of the dependency structure >> of sentences .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This paper proposes a framework in which [[ Lagrangian Particle Dynamics ]] is used for the << segmentation of high density crowd flows >> and detection of flow instabilities .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In our framework , the << structures of classes >> are conceptualized as a [[ semi-Riemannian manifold ]] which is considered as a submanifold embedded in an ambient semi-Riemannian space .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We present an [[ approach ]] that can learn an << object category >> from just its name , by utilizing the raw output of image search engines available on the Internet .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Specifically , a reliable [[ bispectrum mask ]] is generated to guarantee that the << speaker DOA cues >> , derived from BISDR , are robust to NSI in terms of speech sparsity and large bispectrum amplitude of the captured signals .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "A series of tests are described that show the power of the << error correction methodology >> when [[ stereotypic dialogue ]] occurs .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To overcome this limitation , we propose a novel << mapping algorithm >> that derives the relative positioning and orientation between two PTZ cameras based on a [[ unified polynomial model ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The [[ model ]] appears capable of accommodating the sort of << reduplications >> that have been observed to occur in natural languages , but it excludes many of the unnatural constructions that other formal models have permitted .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Moreover , a [[ heuristic approach ]] was commonly used to obtain << translation invariance >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We show that the crucial operation of [[ consistency checking ]] for such << descriptions >> is NP-complete , and therefore probably intractable , but proceed to develop algorithms which can sometimes alleviate the unpleasant consequences of this intractability .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Johnston 1998 presents an approach in which strategies for multimodal integration are stated declaratively using a [[ unification-based grammar ]] that is used by a << multidimensional chart parser >> to compose inputs .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The paper experimentally demonstrates the effectiveness of [[ discriminative patches ]] as an << unsupervised mid-level visual representation >> , suggesting that it could be used in place of visual words for many tasks .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "By those assumptions we cast the problem as a Quadratic Eigenvalue Problem offering an elegant way of treating nonlinear monomials and delivering a [[ quasi closed-form solution ]] as a reliable starting point for a further << bundle adjustment >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Second , we show a << method >> using [[ `` overlapping constraint '' ]] with a Korean-to-English dictionary and an English-to-Japanese dictionary .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Our proposed [[ algorithm ]] first estimates camera viewpoint using rigid structure-from-motion , then reconstructs << object shapes >> by optimizing over visual hull proposals guided by loose within-class shape similarity assumptions .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Other << tasks >> using the [[ method ]] developed for ILIMP are described briefly , as well as the use of ILIMP in a modular syntactic analysis system .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "This poster presents an approach to << spelling correction >> in agglutinative languages that is based on [[ two-level morphology ]] and a dynamic-programming based search algorithm .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We make use of a << conditional log-linear model >> , with [[ hidden variables ]] representing the assignment of lexical items to word clusters or word senses .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Finally , we show that models fine-tuned from our [[ animated GIF description dataset ]] can be helpful for << automatic movie description >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "As [[ unification-based grammatical frameworks ]] are extended to handle richer descriptions of << linguistic information >> , they begin to share many of the properties that have been developed in KL-ONE-like knowledge representation systems .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In this paper , we describe a << phrase-based unigram model >> for statistical machine translation that uses a much simpler set of [[ model parameters ]] than similar phrase-based models .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We present a [[ method ]] for << synthesizing complex , photo-realistic facade images >> , from a single example .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "It is argued that the resulting [[ algorithm ]] is both efficient and flexible and is , therefore , a good choice for the << parser >> used in a natural language interface .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The goal of this research is to develop a [[ spoken language system ]] that will demonstrate the usefulness of voice input for << interactive problem solving >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks : -LRB- 1 -RRB- for predicting subtopic boundaries , the lexical cohesion-based approach alone can achieve competitive results , -LRB- 2 -RRB- for predicting top-level boundaries , the machine learning approach that combines lexical-cohesion and conversational features performs best , and -LRB- 3 -RRB- conversational cues , such as cue phrases and overlapping speech , are better [[ indicators ]] for the << top-level prediction task >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Currently several << grammatical formalisms >> converge towards being declarative and towards utilizing [[ context-free phrase-structure grammar ]] as a backbone , e.g. LFG and PATR-II .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "We apply the [[ boosting method ]] to << parsing >> the Wall Street Journal treebank .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "In our system , features and << decision strategies >> are discovered and trained automatically , using a large body of [[ speech data ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Many promising experimental results on the << real datasets >> including ImageCLEF and [[ Me-diaMill ]] demonstrate the effectiveness and efficiency of the proposed algorithm .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Empirical experience and observations have shown us when powerful and highly tunable << classifiers >> such as maximum entropy classifiers , [[ boosting ]] and SVMs are applied to language processing tasks , it is possible to achieve high accuracies , but eventually their performances all tend to plateau out at around the same point .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Furthermore , we introduce global variables in the model , which can represent << global properties >> such as translation , scale or [[ viewpoint ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "The two << evaluation measures >> of the [[ BLEU score ]] and the NIST score demonstrated the effect of using an out-of-domain bilingual corpus and the possibility of using the language model .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Recently , we initiated a project to develop a << phonetically-based spoken language understanding system >> called [[ SUMMIT ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We evaluate our approach on several standard << datasets >> such as im2gps , San Francisco and [[ MediaEval2010 ]] , and obtain state-of-the-art results .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "The [[ Rete and Treat algorithms ]] are considered the most efficient << implementation techniques >> for Forward Chaining rule systems .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "It is general , i.e. , it can be used to minimize any energy function -LRB- e.g. , unary , pairwise , and higher-order terms -RRB- with any existing << energy minimization algorithm >> -LRB- e.g. , [[ graph cuts ]] and belief propagation -RRB- .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "These << constraints >> are of two types : conditional inde-pendencies and [[ algebraic constraints ]] , first noted by Verma .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Two main classes of << approaches >> have been studied to perform monocular nonrigid 3D reconstruction : Template-based methods and [[ Non-rigid Structure from Motion techniques ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "A method of sense resolution is proposed that is based on WordNet , an on-line lexical database that incorporates << semantic relations >> -LRB- synonymy , antonymy , [[ hyponymy ]] , meronymy , causal and troponymic entailment -RRB- as labeled pointers between word senses .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Furthermore , we introduce global variables in the model , which can represent << global properties >> such as [[ translation ]] , scale or viewpoint .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "First , beyond the aging dictionaries , each subject may have extra << personalized facial characteristics >> , e.g. [[ mole ]] , which are invariant in the aging process .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Ideally , these are basic vocabulary units suitable for different << tasks >> , such as speech and text understanding , machine translation , [[ information retrieval ]] , and statistical language modeling .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "[[ Synchronous dependency insertion grammars ]] are a version of << synchronous grammars >> defined on dependency trees .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "It is achieved by deriving the inter-sensor data ratio model of an AVS in bispectrum domain -LRB- BISDR -RRB- and exploring the << favorable properties >> of bispectrum , such as [[ zero value of Gaussian process ]] and different distribution of speech and NSI .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Extensive experiments show that our method works satisfactorily on challenging image data , which establishes a technical foundation for solving several << computer vision problems >> , such as [[ motion analysis ]] and image restoration , using the blur information .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Furthermore , discrim-inative patches can also be used in a << supervised regime >> , such as [[ scene classification ]] , where they demonstrate state-of-the-art performance on the MIT Indoor-67 dataset .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We compare two wide-coverage << lexicalized grammars of English >> , LEXSYS and [[ XTAG ]] , finding that the two grammars exploit EDOL in different ways .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We show that the newly proposed concept-distance measures outperform traditional distributional word-distance measures in the << tasks >> of -LRB- 1 -RRB- ranking word pairs in order of semantic distance , and -LRB- 2 -RRB- [[ correcting real-word spelling errors ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We also estimate bounds on the Bayes classification error to quantify the distinction between two classes of << HFOs >> -LRB- [[ those ]] occurring during seizures and those occurring due to other processes -RRB- .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Empirical experience and observations have shown us when powerful and highly tunable << classifiers >> such as maximum entropy classifiers , boosting and [[ SVMs ]] are applied to language processing tasks , it is possible to achieve high accuracies , but eventually their performances all tend to plateau out at around the same point .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Because of its adaptive nature , Bayesian learning serves as a unified approach for the following four << speech recognition applications >> , namely parameter smoothing , speaker adaptation , speaker group modeling and [[ corrective training ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "The same system used in a validation mode , can be used to check and spot alignment errors in << multilingually aligned wordnets >> as [[ BalkaNet ]] and EuroWordNet .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We have recently shown that the fusion of measurement information with system dynamics and shape priors greatly improves the tracking performance for very << noisy images >> such as [[ ultrasound sequences ]] -LSB- 22 -RSB- .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Many promising experimental results on the << real datasets >> including [[ ImageCLEF ]] and Me-diaMill demonstrate the effectiveness and efficiency of the proposed algorithm .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Extensive experiments show that our method works satisfactorily on challenging image data , which establishes a technical foundation for solving several << computer vision problems >> , such as motion analysis and [[ image restoration ]] , using the blur information .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Through two experiments , three methods for constructing word vectors , i.e. , LSA-based , cooccurrence-based and dictionary-based methods , were compared in terms of the ability to represent two kinds of << similarity >> , i.e. , taxonomic similarity and [[ associative similarity ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "A method of sense resolution is proposed that is based on WordNet , an on-line lexical database that incorporates << semantic relations >> -LRB- synonymy , [[ antonymy ]] , hyponymy , meronymy , causal and troponymic entailment -RRB- as labeled pointers between word senses .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Specifically , we design two << marginalized denoising auto-encoders >> , one for the target and the [[ other ]] for source as well as the intermediate one .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We propose a method that automatically generates paraphrase sets from seed sentences to be used as reference sets in objective << machine translation evaluation measures >> like [[ BLEU ]] and NIST .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "In this paper we discuss a proposed user knowledge modeling architecture for the [[ ICICLE system ]] , a << language tutoring application >> for deaf learners of written English .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Third , we consider another alternative method rarely used for building a << dictionary >> : an [[ English-to-Korean dictionary ]] and English-to-Japanese dictionary .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "In this work we use the property of << multi scale transforms >> , such as [[ wavelet or wavelet packets ]] , to decompose signals into sets of local features with various degrees of sparsity .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Thus the work reported addresses two << robustness problems >> faced by current experimental natural language processing systems : coping with an incomplete lexicon and with [[ incomplete knowledge of phrasal constructions ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "It is achieved by deriving the inter-sensor data ratio model of an AVS in bispectrum domain -LRB- BISDR -RRB- and exploring the << favorable properties >> of bispectrum , such as zero value of Gaussian process and different [[ distribution of speech and NSI ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks : -LRB- 1 -RRB- for predicting subtopic boundaries , the lexical cohesion-based approach alone can achieve competitive results , -LRB- 2 -RRB- for predicting top-level boundaries , the machine learning approach that combines lexical-cohesion and conversational features performs best , and -LRB- 3 -RRB- << conversational cues >> , such as [[ cue phrases ]] and overlapping speech , are better indicators for the top-level prediction task .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "The answering agents adopt fundamentally different << strategies >> , one utilizing primarily knowledge-based mechanisms and the [[ other ]] adopting statistical techniques .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We have recently reported on two new word-sense disambiguation systems , one trained on bilingual material -LRB- the Canadian Hansards -RRB- and the other trained on << monolingual material >> -LRB- Roget 's Thesaurus and [[ Grolier 's Encyclopedia ]] -RRB- .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Ant-Q algorithms were inspired by work on the [[ ant system -LRB- AS -RRB- ]] , a << distributed algorithm >> for combinatorial optimization based on the metaphor of ant colonies which was recently proposed in -LRB- Dorigo , 1992 ; Dorigo , Maniezzo and Colorni , 1996 -RRB- .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "A new semantic representation is proposed that uses virtual reality 3D scene modeling software to produce << spatially complex ASL phenomena >> called '' [[ classifier predicates ]] . ''", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "However , the current best << serial algorithm >> by Boykov and Kolmogorov -LSB- 4 -RSB- -LRB- called the [[ BK algorithm ]] -RRB- still has the superior empirical performance .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We study the question of how to make loss-aware predictions in image segmentation settings where the << evaluation function >> is the [[ Intersection-over-Union -LRB- IoU -RRB- measure ]] that is used widely in evaluating image segmentation systems .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We present a general method for learning such transformations from an annotated corpus and describe experiments with two << applications >> of the method : identification of non-local depenencies -LRB- using Penn Treebank data -RRB- and [[ semantic role labeling ]] -LRB- using Proposition Bank data -RRB- .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Instead of performing << pixel-domain super-resolution and recognition >> independently as two separate sequential processes , we integrate the tasks of [[ super-resolution ]] and recognition by directly computing a maximum likelihood identity parameter vector in high-resolution tensor space for recognition .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We describe [[ Yoopick ]] , a << combinatorial sports prediction market >> that implements a flexible betting language , and in turn facilitates fine-grained probabilistic estimation of outcomes .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "The principle of this approach is to decompose a recognition process into two << passes >> where the first pass builds the words subset for the [[ second pass recognition ]] by using information retrieval procedure .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "This paper presents a method to estimate the << sense priors of words >> drawn from a [[ new domain ]] , and highlights the importance of using well calibrated probabilities when performing these estimations .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "This paper demonstrates that match with respect to domain and time is also important , and presents preliminary experiments with << training data >> labeled with [[ emoticons ]] , which has the potential of being independent of domain , topic and time .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "We built a novel , extensive << dataset >> on [[ geometric context of video ]] to evaluate our method , consisting of over 100 ground-truth annotated outdoor videos with over 20,000 frames .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "In particular , it describes a robust explanation system that constructs multisentential and multi-paragraph explanations from the a << large-scale knowledge base >> in the domain of botanical anatomy , [[ physiology ]] , and development .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "The SDT representation is an analytic expression and following the theoretical physics literature , can be normalized to have unit L2 norm-making it a square-root density , which is identified with a point on a << unit Hilbert sphere >> , whose [[ intrinsic geometry ]] is fully known .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "Which in turn leads to a better << model >> in terms of [[ modes of variations ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "This demonstrates << relighting >> with [[ reproduction of fine surface detail ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "A unique characteristic of the system is its ability to cope with long-duration and complete occlusion without a [[ prior knowledge ]] about the shape or << motion of objects >> .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "These results suggest the NPV does not give a faithful << image of cortical processing >> during [[ arm reaching movements ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "They demonstrate a reduced drift and increased [[ robustness ]] to large << non-rigid deformations >> .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "With the recent popularity of << animated GIFs >> on [[ social media ]] , there is need for ways to index them with rich meta-data .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "The proposed << scheme >> eliminates redundant copying while maintaining the [[ quasi-destructive scheme 's ability ]] to avoid over copying and early copying combined with its ability to handle cyclic structures without algorithmic additions .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "In this paper , we identify [[ features ]] of << electronic discussions >> that influence the clustering process , and offer a filtering mechanism that removes undesirable influences .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "<< Synchronous dependency insertion grammars >> are a version of synchronous grammars defined on [[ dependency trees ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "We describe both the [[ syntax ]] and semantics of a general << propositional language of context >> , and give a Hilbert style proof system for this language .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "Instead of performing pixel-domain super-resolution and recognition independently as two separate sequential processes , we integrate the tasks of super-resolution and recognition by directly computing a << maximum likelihood identity parameter vector >> in [[ high-resolution tensor space ]] for recognition .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "With the improvements in accuracy the motion estimation is now rather limited by imperfections in the CCD sensors , especially the [[ spatial nonuni-formity ]] in the << responsivity >> .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "For example , after translation into an equivalent RCG , any << tree adjoining grammar >> can be parsed in [[ O -LRB- n6 -RRB- time ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "In particular , it describes a robust explanation system that constructs multisentential and multi-paragraph explanations from the a << large-scale knowledge base >> in the domain of [[ botanical anatomy ]] , physiology , and development .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "The advantage of this novel method is that it clusters all [[ inflected forms ]] of an << ambiguous word >> in one classifier , therefore augmenting the training material available to the algorithm .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "To obtain a more complete list of MWEs we propose and use a technique exploiting the << Word Sketch Engine >> , which allows us to work with [[ statistical parameters ]] such as frequency of MWEs and their components as well as with the salience for the whole MWEs .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "We present the computational model for POS learning , and present results for applying it to << Bulgarian >> , a Slavic language with relatively [[ free word order ]] and rich morphology .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "These << models >> can be viewed as pairs of [[ probabilistic context-free grammars ]] working in a ` synchronous ' way .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "This study compares the effect of [[ noise ]] and reverberation on << depression prediction >> using 1 -RRB- standard mel-frequency cepstral coefficients -LRB- MFCCs -RRB- , and 2 -RRB- features designed for noise robustness , damped oscillator cepstral coefficients -LRB- DOCCs -RRB- .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "However , for ultra-wide baselines , as in the case of << aerial images >> captured under [[ large camera rotations ]] , the appearance variation goes beyond the reach of SIFT and RANSAC .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "Implementation and empirical results are described for the the analysis of [[ dependency structures ]] of << Japanese patent claim sentences >> .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "A novel evaluation scheme is proposed which accounts for the effect of [[ polysemy ]] on the << clusters >> , offering us a good insight into the potential and limitations of semantically classifying undisambiguated SCF data .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "We describe the use of << text data >> scraped from the [[ web ]] to augment language models for Automatic Speech Recognition and Keyword Search for Low Resource Languages .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "On the << hypothesis network >> , individual information is integrated and an optimal [[ internal model ]] of perceptual sounds is automatically constructed .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "The << method >> combined the [[ log-likelihood ]] under a baseline model -LRB- that of Collins -LSB- 1999 -RSB- -RRB- with evidence from an additional 500,000 features over parse trees that were not included in the original model .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Different from previous studies , we propose an approximate phrase mapping algorithm and incorporate the [[ mapping score ]] into the << correlation measure >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "This paper presents an analysis of << temporal anaphora >> in sentences which contain [[ quantification over events ]] , within the framework of Discourse Representation Theory .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "The work presented in this paper is the first step in a project which aims to cluster and summarise [[ electronic discussions ]] in the context of << help-desk applications >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "The << demonstrator >> embodies an interesting combination of hand-built , symbolic resources and [[ stochastic processes ]] .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "We describe an implementation of data-driven selection of emphatic facial displays for an [[ embodied conversational agent ]] in a << dialogue system >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "We further show the usefulness of dormant independencies in model testing and induction by giving an algorithm that uses constraints entailed by dormant independencies to prune [[ extraneous edges ]] from a given << causal graph >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Each << generalized metaphor >> contains a recognition network , a basic mapping , additional transfer mappings , and an [[ implicit intention component ]] .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Some of the << principles >> which are relevant to the topic of this paper are : -LRB- a -RRB- [[ Multiple Layer of Grammars ]] -LRB- b -RRB- Multiple Layer Presentation -LRB- c -RRB- Lexicon Driven Processing -LRB- d -RRB- Form-Oriented Dictionary Description .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Our experiments show that punctuation is of little help in parsing spoken language and extracting [[ subcategorization cues ]] from << spoken language >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "From this , a [[ language learning model ]] was implemented in the program << RINA >> , which enhances its own lexical hierarchy by processing examples in context .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "<< Multimedia answers >> include [[ videodisc images ]] and heuristically-produced complete sentences in text or text-to-speech form .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "The << demonstrator >> embodies an interesting combination of [[ hand-built , symbolic resources ]] and stochastic processes .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "This paper shows that it is very often possible to identify the source language of [[ medium-length speeches ]] in the << EUROPARL corpus >> on the basis of frequency counts of word n-grams -LRB- 87.2 % -96.7 % accuracy depending on classification method -RRB- .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "The << representation >> contains [[ complementary information ]] to that learned from supervised image datasets like ImageNet .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "An experimental << system >> embodying this [[ mechanism ]] has been implemented for processing definitions from the Longman Dictionary of Contemporary English .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "This paper proposes a method for learning joint embed-dings of images and text using a << two-branch neural network >> with [[ multiple layers of linear projections ]] followed by nonlinearities .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "In our framework , the structures of classes are conceptualized as a semi-Riemannian manifold which is considered as a [[ submanifold ]] embedded in an << ambient semi-Riemannian space >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "The proposed << mechanism >> includes title-driven name recognition , [[ adaptive dynamic word formation ]] , identification of 2-character and 3-character Chinese names without title .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Motivated by these arguments , we introduce a number of new << performance enhancing techniques >> including [[ part of speech tagging ]] , new similarity measures and expanded stop lists .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Our aim is to revisit the present-day [[ syntactico-semantic -LRB- tectogrammatical -RRB- annotation ]] in the << Prague Dependency Treebank >> , extend it for the purposes of a sentence-boundary-crossing representation and eventually to design a new , discourse level of annotation .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "This << system >> consists of one or more reference times and [[ temporal perspective times ]] , the speech time and the location time .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Our << model >> consists of multiple [[ processing modules ]] and a hypothesis network for quantitative integration of multiple sources of information .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "We use a convex formulation of the multi-label Potts model with label costs and show that the [[ asymmetric map-uniqueness criterion ]] can be integrated into our << formulation >> by means of convex constraints .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "This paper shows how the process of fitting a lexicalized grammar to a domain can be automated to a great extent by using a << hybrid system >> that combines traditional [[ knowledge-based techniques ]] with a corpus-based approach .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Unlike the quantitative prior , the qualitative prior is often ignored due to the difficulty of incorporating [[ them ]] into the << model learning process >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "Two [[ themes ]] have evolved in << speech and text image processing >> work at Xerox PARC that expand and redefine the role of recognition technology in document-oriented applications .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "In this paper , we describe the research using machine learning techniques to build a [[ comma checker ]] to be integrated in a << grammar checker >> for Basque .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "At the same time , the recent improvements in the [[ BLEU scores ]] of << statistical machine translation -LRB- SMT -RRB- >> suggests that SMT models are good at predicting the right translation of the words in source language sentences .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We applied the proposed << method >> to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and a [[ kernel function ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The experimental results demonstrate that the proposed << method >> makes it possible to significantly improve speech quality in the converted singing voice while preserving the [[ conversion accuracy of singer identity ]] compared to the conventional SVC .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "When used as pre-training for action recognition , << our method >> gives significant gains over learning without external data on [[ benchmark datasets ]] like UCF101 and HMDB51 .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "This paper presents an [[ evaluation method ]] employing a latent variable model for << paraphrases >> with their contexts .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "A larger << model >> trained after the deadline achieves 80.5 % [[ macro-average F1 ]] , 87.6 % syntactic dependencies LAS , and 73.1 % semantic dependencies F1 .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We demonstrate that our models outperform the << state-of-the-art >> on [[ ultra-wide baseline matching ]] and approach human accuracy .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We investigate that claim by adopting a simple MT-based paraphrasing technique and evaluating << QA system >> performance on [[ paraphrased questions ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We applied the proposed << method >> to question classification and sentence alignment tasks to evaluate its performance as a [[ similarity measure ]] and a kernel function .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The [[ PDTB ]] is being built directly on top of the Penn TreeBank and Propbank , thus supporting the extraction of useful syntactic and semantic features and providing a richer substrate for the development and evaluation of << practical algorithms >> .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Since the significance of words differs in IR , << automatic speech recognition -LRB- ASR -RRB- >> performance has been evaluated based on [[ weighted word error rate -LRB- WWER -RRB- ]] , which gives a weight on errors from the viewpoint of IR , instead of word error rate -LRB- WER -RRB- , which treats all words uniformly .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Our experiments demonstrate that our << approach >> yields much more accurate [[ 3D reconstructions ]] than state-of-the-art techniques .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The performance of SRDA is tested on [[ face recognition -LRB- singular case ]] -RRB- and handwritten capital letter classification -LRB- nonsingular case -RRB- against existing << algorithms >> .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Following recent developments in the [[ automatic evaluation ]] of machine translation and << document summarization >> , we present a similar approach , implemented in a measure called POURPRE , for automatically evaluating answers to definition questions .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "In head-to-head tests against one of the best existing robust probabilistic parsing models , which we call P-CFG , the << HBG model >> significantly outperforms P-CFG , increasing the [[ parsing accuracy rate ]] from 60 % to 75 % , a 37 % reduction in error .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The preliminary experiments prove that the << s-VSM model >> outperforms the VSM model in the [[ lyric-based song sentiment classification task ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "[[ Evaluations ]] conducted on two different domains for << Chinese term extraction >> show significant improvements over existing techniques which verifies its efficiency and domain independent nature .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We evaluate our << approach >> on several standard [[ datasets ]] such as im2gps , San Francisco and MediaEval2010 , and obtain state-of-the-art results .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Effectiveness of the proposed << framework >> was confirmed in the [[ success rate of retrieval ]] and the average number of turns for information access .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Our results not only show that similar distinguishing speech processes were identified ; our APT-based classifier yielded better [[ classification accuracy ]] than the << MPT-based classifier >> whilst using fewer classification features .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The submitted model yields 79.1 % macro-average F1 performance , for the joint << task >> , 86.9 % [[ syntactic dependencies LAS ]] and 71.0 % semantic dependencies F1 .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The accuracy of the << tensor method >> is verified with computer-generated sequences and a [[ calibrated image sequence ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We compare the lexically-induced relations with the original << MeSH relations >> : after a quantitative evaluation of their congruence through [[ recall and precision metrics ]] , we perform a qualitative , human analysis ofthe ` new ' relations not present in the MeSH .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Performance of each investigated << classifier >> is evaluated both via receiving operating curve and via a [[ measure ]] , called mean absolute error , related to the quality in predicting the corresponding word error rate .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The [[ NormF ]] of the best summary and that of the fixed summary for << categorization task >> are 0.4090 and 0.4023 .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Experimental results demonstrate that our proposed << algorithm >> presents substantially reduced computational complexity and improved flexibility at the cost of slightly decreased [[ pixel accuracy ]] , as compared with the work of Chen and Wang .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Experiments evaluating the effectiveness of our answer resolution algorithm show a 35.0 % relative improvement over our << baseline system >> in the number of questions correctly answered , and a 32.8 % improvement according to the [[ average precision metric ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "In experiments using the Penn WSJ corpus , our automatically trained << model >> gave a performance of 86.6 % -LRB- [[ F1 ]] , sentences < 40 words -RRB- , which is comparable to that of an unlexicalized PCFG parser created using extensive manual feature selection .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Recently considerable progress has been made by a number of groups involved in the DARPA Spoken Language Systems -LRB- SLS -RRB- program to agree on a methodology for comparative evaluation of SLS systems , and that [[ methodology ]] has been put into practice several times in comparative tests of several << SLS systems >> .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Observing that the quality of the lexicon greatly impacts the [[ accuracy ]] that can be achieved by the << algorithms >> , we present a method of HMM training that improves accuracy when training of lexical probabilities is unstable .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "[[ Speech recognition ]] experiments in simulated and real reverberant environments show the efficiency of our approach which outperforms standard << channel normaliza-tion techniques >> .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The new << model >> achieved 89.75 % [[ F-measure ]] , a 13 % relative decrease in F-measure error over the baseline model 's score of 88.2 % .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We show results from << multi-modal super-resolution and face recognition >> experiments across different imaging modalities , using low-resolution images as testing inputs and demonstrate improved [[ recognition rates ]] over standard tensorface and eigenface representations .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "It demonstrates that the proposed << cluster tree >> achieves better [[ temporal consistency ]] than the previous sequential and non-sequential tracking approaches .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Furthermore , discrim-inative patches can also be used in a supervised regime , such as scene classification , where << they >> demonstrate state-of-the-art performance on the [[ MIT Indoor-67 dataset ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The [[ precision rate ]] for << ILIMP >> is 97,5 % .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Although Bikel 's parser achieves a higher accuracy for parsing written language , << it >> achieves a higher [[ accuracy ]] when extracting subcategorization cues from spoken language .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Finally , a measurement campaign is conducted and the functionality of the << estimation method >> is verified on [[ real data ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "In spite of the level of difficulty of the challenge , the model nevertheless produces fluent output as judged by human evaluators , and performs significantly better than widely used << phrase-based SMT models >> upon the same [[ task ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "After several experiments , and trained with a little corpus of 100,000 words , the << system >> guesses correctly not placing commas with a precision of 96 % and a [[ recall ]] of 98 % .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "In experiments using the [[ Penn WSJ corpus ]] , our automatically trained << model >> gave a performance of 86.6 % -LRB- F1 , sentences < 40 words -RRB- , which is comparable to that of an unlexicalized PCFG parser created using extensive manual feature selection .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Finally , we evaluate the << approach >> in a working [[ multi-page system ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The accuracy of the << tensor method >> is verified with [[ computer-generated sequences ]] and a calibrated image sequence .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "In this paper the << LIMSI recognizer >> which was evaluated in the ARPA NOV93 CSR test is described , and experimental results on the [[ WSJ and BREF corpora ]] under closely matched conditions are reported .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We conclude by showing how our design can provide a rich and robust information base to a language assessment / correction application by modeling << user proficiency >> at a high level of granularity and [[ specificity ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The results show that << it >> can provide a significant improvement in [[ alignment quality ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Our << resource-frugal approach >> results in 87.5 % [[ agreement ]] with a state of the art , proprietary Arabic stemmer built using rules , affix lists , and human annotated text , in addition to an unsupervised component .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Through experiments with parallel corpora of a Korean and English language pairs , we show that our paraphrasing method effectively extracts paraphrases with high precision , 94.3 % and 84.6 % respectively for Korean and English , and the << translation knowledge >> extracted from the bilingual corpora could be generalized successfully using the paraphrases with the 12.5 % [[ compression ratio ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "In this paper , we compare the relative effects of segment order , segmentation and segment contiguity on the [[ retrieval ]] performance of a << translation memory system >> .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Experimental results demonstrate that our proposed << algorithm >> presents substantially reduced [[ computational complexity ]] and improved flexibility at the cost of slightly decreased pixel accuracy , as compared with the work of Chen and Wang .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "This paper describes a characters-based Chinese collocation system and discusses the advantages of [[ it ]] over a traditional << word-based system >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "For one thing , learning methodology applicable in [[ general domains ]] does not readily lend itself in the << linguistic domain >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "We show that [[ SHORTSTR2 ]] is complementary to the existing algorithms SHORTGAC and << HAGGISGAC >> that exploit short supports , while being much simpler .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Performance of the [[ algorithm ]] is contrasted with << human annotation >> performance .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Using our [[ approach ]] we are able to intelligently segment scenes with objects of greater complexity than previous << physics-based segmentation algorithms >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "The accuracy of the [[ statistical method ]] is reasonably good , comparable to << taggers >> for English .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "The performance of [[ SRDA ]] is tested on face recognition -LRB- singular case -RRB- and handwritten capital letter classification -LRB- nonsingular case -RRB- against existing << algorithms >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Sentence ambiguities can be resolved by using [[ domain targeted preference knowledge ]] without using complicated large << knowledgebases >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "The experimental results will show that [[ it ]] significantly outperforms state-of-the-art << approaches >> in sentence-level correlation .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Specifically , this system is designed to deterministically choose between [[ pronominalization ]] , << superordinate substitution >> , and definite noun phrase reiteration .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "We demonstrate that our [[ models ]] outperform the << state-of-the-art >> on ultra-wide baseline matching and approach human accuracy .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "The [[ method ]] overcomes the limitations of conventional << statistical methods >> which require large corpora to be effective , and lexical approaches which depend on existing bilingual dictionaries .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "We demonstrate the merits of our approach by comparing [[ it ]] to previous << methods >> on both synthetic and natural datasets .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Our experiments show that [[ log-linear models ]] significantly outperform << IBM translation models >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Unlike previous [[ studies ]] that focus on user 's knowledge or typical kinds of users , the << user model >> we propose is more comprehensive .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "In our experiments , the [[ method ]] achieves a TRDR score that is significantly higher than that of the << baseline >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Extensive experiments on both image and video interestingness benchmark datasets demonstrate that our new [[ approach ]] significantly outperforms << state-of-the-art alternatives >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Our [[ resource-frugal approach ]] results in 87.5 % agreement with a state of the art , proprietary << Arabic stemmer >> built using rules , affix lists , and human annotated text , in addition to an unsupervised component .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Surprisingly however , the << WSD accuracy >> of SMT models has never been evaluated and compared with [[ that ]] of the dedicated WSD models .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "[[ Understanding natural images ]] has been extensively studied in computer vision , while << diagram understanding >> has received little attention .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Our [[ algorithms ]] outperform << baseline seg-mentation algorithms >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "While << conditional independencies >> are well studied and frequently used in causal induction algorithms , [[ Verma constraints ]] are still poorly understood , and rarely applied .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Our experiments demonstrate that our [[ approach ]] yields much more accurate 3D reconstructions than << state-of-the-art techniques >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "We perform extensive statistical analyses to compare our [[ dataset ]] to existing << image and video description datasets >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Our [[ system ]] outperforms the average << system >> in categorization task but does a common job in adhoc task .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Extensive experiments well demonstrate the advantages of our proposed [[ solution ]] over other << state-of-the-arts >> in term of personalized aging progression , as well as the performance gain for cross-age face verification by synthesizing aging faces .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "In addition , combination of the training speakers is done by [[ averaging the statistics of independently trained models ]] rather than the usual << pooling of all the speech data >> from many speakers prior to training .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We measured the quality of the paraphrases produced in an experiment , i.e. , -LRB- i -RRB- their grammaticality : at least 99 % correct sentences ; -LRB- ii -RRB- their << equivalence in meaning >> : at least 96 % correct paraphrases either by meaning equivalence or entailment ; and , -LRB- iii -RRB- the amount of [[ internal lexical and syntactical variation ]] in a set of paraphrases : slightly superior to that of hand-produced sets .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We present the computational model for POS learning , and present results for applying it to Bulgarian , a Slavic language with relatively [[ free word order ]] and << rich morphology >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "In our system , [[ features ]] and << decision strategies >> are discovered and trained automatically , using a large body of speech data .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Our approach yields [[ phrasal and single word lexical paraphrases ]] as well as << syntactic paraphrases >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Many << description logics -LRB- DLs -RRB- >> combine [[ knowledge representation ]] on an abstract , logical level with an interface to `` concrete '' domains such as numbers and strings .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Results from experiments with word dependent substitution costs will demonstrate an additional increase of correlation between [[ automatic evaluation measures ]] and << human judgment >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We show that the newly proposed concept-distance measures outperform traditional distributional word-distance measures in the tasks of -LRB- 1 -RRB- << ranking word pairs in order of semantic distance >> , and -LRB- 2 -RRB- [[ correcting real-word spelling errors ]] .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Joint image filters can leverage the guidance image as a prior and transfer the structural details from the guidance image to the target image for [[ suppressing noise ]] or << enhancing spatial resolution >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The [[ quantization ]] and the << indexing >> are therefore fully integrated , essentially being one and the same .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "It is general , i.e. , it can be used to minimize any energy function -LRB- e.g. , unary , pairwise , and higher-order terms -RRB- with any existing energy minimization algorithm -LRB- e.g. , [[ graph cuts ]] and << belief propagation >> -RRB- .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "In this paper , we compare the relative effects of [[ segment order ]] , << segmentation >> and segment contiguity on the retrieval performance of a translation memory system .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We also show that : Supporting full unification is costly ; Full unification is not used frequently ; A combination of [[ compile time ]] and << run time >> checks can determine when full unification is not needed .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "For categorization task , [[ positive feature vectors ]] and << negative feature vectors >> are used cooperatively to construct generic , indicative summaries .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The recognizer uses a << time-synchronous graph-search strategy >> which is shown to still be viable with a 20k-word vocabulary when used with [[ bigram back-off language models ]] .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Specifically , we design two marginalized denoising auto-encoders , [[ one ]] for the target and the << other >> for source as well as the intermediate one .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "This method can be used in applications such as [[ information retrieval ]] , << routing >> , and text summarization .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "This paper shows how the process of fitting a lexicalized grammar to a domain can be automated to a great extent by using a hybrid system that combines traditional [[ knowledge-based techniques ]] with a << corpus-based approach >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Instead of performing pixel-domain super-resolution and recognition independently as two separate sequential processes , we integrate the tasks of [[ super-resolution ]] and << recognition >> by directly computing a maximum likelihood identity parameter vector in high-resolution tensor space for recognition .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "For solving this problem a novel optimization scheme , called Priority-BP , is proposed which carries two very important extensions over standard belief propagation -LRB- BP -RRB- : '' [[ priority-based message scheduling ]] '' and '' << dynamic label pruning >> '' .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We use a maximum likelihood criterion to train a log-linear block bigram model which uses [[ real-valued features ]] -LRB- e.g. a language model score -RRB- as well as << binary features >> based on the block identities themselves , e.g. block bigram features .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The research effort focusses on developing advanced acoustic modelling , [[ rapid search ]] , and << recognition-time adaptation techniques >> for robust large-vocabulary CSR , and on applying these techniques to the new ARPA large-vocabulary CSR corpora and to military application tasks .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Furthermore , the maximum margin criterion , e.g. , [[ intra-class com-pactness ]] and << inter-class penalty >> , on the output layer is imposed to seek more discriminative features across different domains .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "A method of sense resolution is proposed that is based on WordNet , an on-line lexical database that incorporates semantic relations -LRB- [[ synonymy ]] , << antonymy >> , hyponymy , meronymy , causal and troponymic entailment -RRB- as labeled pointers between word senses .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "When classifying high-dimensional sequence data , traditional methods -LRB- e.g. , [[ HMMs ]] , << CRFs >> -RRB- may require large amounts of training data to avoid overfitting .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Stochastic attention-based models have been shown to improve computational efficiency at test time , but they remain difficult to train because of [[ intractable posterior inference ]] and high variance in the << stochastic gradient estimates >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "[[ Factor analysis ]] and << principal components analysis >> can be used to model linear relationships between observed variables and linearly map high-dimensional data to a lower-dimensional hidden space .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We develop Wallflower , a three-component system for background maintenance : the [[ pixel-level component ]] performs Wiener filtering to make probabilistic predictions of the expected background ; the << region-level component >> fills in homogeneous regions of foreground objects ; and the frame-level component detects sudden , global changes in the image and swaps in better approximations of the background .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Although our experiments are focused on parsing , the techniques described generalize naturally to << NLP structures >> other than [[ parse trees ]] .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We build probabilistic decision trees of different flavors and integrate each of << them >> with the [[ clustering framework ]] .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "In a motorized vehicle a number of easily measurable signals with frequency components related to the rotational speed of the engine can be found , e.g. , vibrations , [[ electrical system voltage level ]] , and << ambient sound >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "An alternative index could be the activity such as [[ discussing ]] , << planning >> , informing , story-telling , etc. .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks : -LRB- 1 -RRB- for predicting subtopic boundaries , the lexical cohesion-based approach alone can achieve competitive results , -LRB- 2 -RRB- for predicting top-level boundaries , the << machine learning approach >> that combines [[ lexical-cohesion and conversational features ]] performs best , and -LRB- 3 -RRB- conversational cues , such as cue phrases and overlapping speech , are better indicators for the top-level prediction task .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "In this paper , we introduce a closed-form solution to systematically combine the [[ limited training data ]] with some generic << qualitative knowledge >> for BN parameter learning .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Specifically , the following components of the system are described : the syntactic analyzer , based on a Procedural Systemic Grammar , the [[ semantic analyzer ]] relying on the Conceptual Dependency Theory , and the << dictionary >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We show how we have integrated into the framework several levels of knowledge for a particular domain , ideas from cognitive semantics and construction grammar , plus tools from [[ prior NLP ]] and << IE research >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We describe both the [[ syntax ]] and << semantics >> of a general propositional language of context , and give a Hilbert style proof system for this language .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We show that our method can greatly speed up the training time for stochastic attention networks in the domains of [[ image classification ]] and << caption generation >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "In this paper we formulate [[ story link detection ]] and << new event detection >> as information retrieval task and hypothesize on the impact of precision and recall on both systems .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The proposed method is evaluated on synthetic data , [[ medical images ]] and << hand contours >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "PAKTUS supports the adaptation of the generic core to a variety of domains : JINTACCS messages , RAINFORM messages , news reports about a specific type of event , such as financial transfers or terrorist acts , etc. , by acquiring sublanguage and domain-specific grammar , words , [[ conceptual mappings ]] , and << discourse patterns >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "One is the development of [[ systems ]] that provide functionality similar to that of << text processors >> but operate directly on audio and scanned image data .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "While it is generic , we demonstrate it on the combination of an [[ image ]] and a << dense depth map >> which give complementary object information .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Some of the principles which are relevant to the topic of this paper are : -LRB- a -RRB- Multiple Layer of Grammars -LRB- b -RRB- [[ Multiple Layer Presentation ]] -LRB- c -RRB- << Lexicon Driven Processing >> -LRB- d -RRB- Form-Oriented Dictionary Description .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Second , we show a method using `` overlapping constraint '' with a [[ Korean-to-English dictionary ]] and an << English-to-Japanese dictionary >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Pipelined Natural Language Generation -LRB- NLG -RRB- systems have grown increasingly complex as architectural modules were added to support language functionalities such as [[ referring expressions ]] , << lexical choice >> , and revision .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The [[ left-side dependents ]] and << right-side nominal dependents >> are detected in Phase I , and right-side verbal dependents are decided in Phase II .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "These applications require high accuracy for the estimation of the motion field since the most interesting parameters of the dynamical processes studied are contained in [[ first-order derivatives of the motion field ]] or in << dynamical changes of the moving objects >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Thereby a system of relevant times provided by the [[ preceeding text ]] and by the << temporal adverbials >> of the sentence being processed is used .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "An alternative index could be the activity such as discussing , [[ planning ]] , << informing >> , story-telling , etc. .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The compact description of a video sequence through a single image map and a dominant motion has applications in several domains , including video browsing and retrieval , [[ compression ]] , << mosaicing >> , and visual summarization .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The anaphoric component is used to define linguistic phenomena such as [[ wh-movement ]] , << the passive and the binding of reflexives and pronouns >> mono-lingually .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The system participated in all the tracks of the segmentation bakeoff -- PK-open , PK-closed , AS-open , [[ AS-closed ]] , << HK-open >> , HK-closed , MSR-open and MSR - closed -- and achieved the state-of-the-art performance in MSR-open , MSR-close and PK-open tracks .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Unfortunately , such estimates would typically require the relations -LRB- scale factors -RRB- between the [[ frequency components ]] and the << speed >> for different gears to be known .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We then extend this approach to account for the availability of heterogeneous data modalities such as [[ geo-tags ]] and << videos >> pertaining to different locations , and also study a relatively under-addressed problem of transferring knowledge available from certain locations to infer the grouping of data from novel locations .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Each generalized metaphor contains a recognition network , a << basic mapping >> , additional [[ transfer mappings ]] , and an implicit intention component .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "The intended use of the [[ algorithm ]] is with robust << hypothesize-and-test frameworks >> such as RANSAC .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Based on the model , a music scene analysis system has been developed for acoustic signals of ensemble music , which recognizes rhythm , [[ chords ]] , and << source-separated musical notes >> .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "Experimental results show that our approach improves domain-specific word alignment in terms of both [[ precision ]] and << recall >> , achieving a relative error rate reduction of 6.56 % as compared with the state-of-the-art technologies .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We show that the suggested hybrid proba-bilistic model -LRB- which combines global variables , like translation , with local variables , like relative positions and appearances of body parts -RRB- , leads to : -LRB- i -RRB- [[ faster convergence ]] of learning phase , -LRB- ii -RRB- << robustness >> to occlusions , and , -LRB- iii -RRB- higher recognition rate .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "A method of sense resolution is proposed that is based on WordNet , an on-line lexical database that incorporates semantic relations -LRB- synonymy , antonymy , hyponymy , [[ meronymy ]] , << causal and troponymic entailment >> -RRB- as labeled pointers between word senses .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "As evidence of its usefulness and usability , it has been used successfully in a research context to uncover relationships between language and behavioral patterns in two distinct domains : [[ tutorial dialogue ]] -LRB- Kumar et al. , submitted -RRB- and << on-line communities >> -LRB- Arguello et al. , 2006 -RRB- .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "By extensive experiments , we show that our learned representation can significantly boost several video recognition tasks -LRB- [[ retrieval ]] , << classification >> , and highlight detection -RRB- over traditional video representations .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "It is expected that incorporation of appropriate [[ N-best candidates of ASR ]] and << contextual information >> will improve the system performance .", "aspect": "scii"}]