CSS-LM

1
[{"sentiment": "FEATURE-OF", "sentence": "On a subset of the most difficult SENSEVAL-2 nouns , the accuracy difference between the two approaches is only 14.0 % , and the difference could narrow further to 6.5 % if we disregard the advantage that << manually sense-tagged data >> have in their [[ sense coverage ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "For this purpose , we have designed a version of KL-ONE which represents the epistemological level , while the new experimental language , << KL-Conc >> , represents the [[ conceptual level ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "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": "FEATURE-OF", "sentence": "This paper presents an algorithm for << labeling curvilinear structure >> at multiple scales in [[ line drawings ]] and edge images Symbolic CURVE-ELEMENT tokens residing in a spatially-indexed and scale-indexed data structure denote circular arcs fit to image data .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "The article also introduces a new algorithm for the boosting approach which takes advantage of the [[ sparsity of the feature space ]] in the << parsing data >> .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "In comparison with earlier work , the proposed method covers a much wider range of verb entailment types and learns the << mapping between verbs >> with [[ highly varied argument structures ]] .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "Little is thus known about the << robustness >> of [[ speech cues ]] in the wild .", "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": "The network is trained using a << large-margin objective >> that combines [[ cross-view ranking constraints ]] with within-view neighborhood structure preservation constraints inspired by metric learning literature .", "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": "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": "FEATURE-OF", "sentence": "Most existing algorithms require the prior knowledge of intrinsic parameters of the PTZ camera to infer the relative positioning and [[ orientation ]] among multiple << PTZ cameras >> .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "<< Polymorphemic stems >> not explicitly stored in the lexicon are given a [[ compositional interpretation ]] .", "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": "The network is trained using a << large-margin objective >> that combines cross-view ranking constraints with [[ within-view neighborhood structure preservation constraints ]] inspired by metric learning literature .", "aspect": "scii"}, {"sentiment": "FEATURE-OF", "sentence": "Novel tilings can then be created , yielding << facade textures >> with different dimensions or with [[ occluded parts inpainted ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "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": "HYPONYM-OF", "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": "HYPONYM-OF", "sentence": "This method can be used in << applications >> such as information retrieval , [[ routing ]] , and text summarization .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "Interdisciplinary evidence from social and cognitive psychology is cited and the prospect of the integration of focus via FDA as a discourse-level construct into << speech synthesis systems >> , in particular , [[ concept-to-speech systems ]] , is also briefly discussed .", "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 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": "HYPONYM-OF", "sentence": "This approach is sufficient for languages with little inflection such as English , but fails for << highly inflective languages >> such as Czech , Russian , Slovak or other [[ Slavonic languages ]] .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "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": "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": "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": "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": "HYPONYM-OF", "sentence": "We present two methods for capturing nonstationary chaos , then present a few << examples >> including [[ biological signals ]] , ocean waves and traffic flow .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "[[ Image matching ]] is a fundamental problem in << Computer Vision >> .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "sentence": "We used a specialized vocabulary for an English certification test as the target vocabulary and used [[ English Wikipedia ]] , a << free-content encyclopedia >> , as the target corpus .", "aspect": "scii"}, {"sentiment": "HYPONYM-OF", "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": "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": "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": "Motivated by the intuition that it often underlies the local structure of coherent text , we develop a << method >> that discovers verb entailment using evidence about [[ discourse relations ]] between clauses available in a parsed corpus .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "However , most existing techniques require expensive and laborious [[ data annotation ]] for << model training >> .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Firstly , the system was based on a linear Support Vector Machine -LRB- SVM -RRB- classifier where << classification progress >> can be implemented easily and quickly in [[ embedded hardware ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "To make the annotation less subjective and more reliable , recent studies employ [[ crowdsourcing tools ]] to collect << pairwise comparisons >> -- relying on majority voting to prune the annotation outliers/errors .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Machine reading is a relatively new field that features [[ computer programs ]] designed to read flowing text and extract << fact assertions >> expressed by the narrative content .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "While this task has much in common with [[ paraphrases acquisition ]] which aims to discover << semantic equivalence >> between verbs , the main challenge of entailment acquisition is to capture asymmetric , or directional , relations .", "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": "Based on this assumption , the [[ algorithm ]] simultaneously estimates << 3D shape and motion >> for each time frame , learns the parameters of the Gaussian , and robustly fills-in missing data points .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ Probabilistic models ]] have been previously shown to be efficient and effective for << modeling and recognition of human motion >> .", "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": "In this paper , << intrinsic topology of multidimensional continuous facial >> affect data is first modeled by an [[ ordinal man-ifold ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "The [[ estimation ]] is then used to select the best << acoustic model >> out of a library of models trained in various artificial re-verberant conditions .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "[[ Automatic image annotation ]] is a newly developed and promising technique to provide << semantic image retrieval >> via text descriptions .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "<< Existing methods >> rely on various kinds of explicit filter construction or [[ hand-designed objective functions ]] .", "aspect": "scii"}, {"sentiment": "USED-FOR", "sentence": "Experimental results are presented to compare LNMF with the [[ NMF and PCA methods ]] for << face representation and recognition >> , which demonstrates advantages of LNMF .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Finally , we evaluate the << approach >> in a working [[ multi-page system ]] .", "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": "We show how << sampling >> can be used to reduce the [[ retrieval time ]] by orders of magnitude with no loss in translation quality .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "The use of BLEU at the character level eliminates the word segmentation problem : [[ it ]] makes it possible to directly compare << commercial systems >> outputting unsegmented texts with , for instance , statistical MT systems which usually segment their outputs .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "In experimental evaluation , our proposed << method >> outperforms previous shift-reduce dependency parsers for the [[ Chine language ]] , showing improvement of dependency accuracy by 10.08 % .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "This mining procedure of AND and OR patterns is readily integrated to << boosting >> , which improves the [[ generalization ability ]] over the conventional boosting decision trees and boosting decision stumps .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "Experimental results show that our << method >> significantly outperforms state-of-the-art syntactic relation-based methods by up to 20 % in [[ MRR ]] .", "aspect": "scii"}, {"sentiment": "EVALUATE-FOR", "sentence": "We build three [[ real-world datasets ]] to benchmark << fine-grained change detection of misaligned scenes >> under varied multiple lighting conditions .", "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": "Experiments on the [[ LabelMe data set ]] showed that the proposed << models >> significantly out-perform a baseline global feature-based approach .", "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": "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": "However , [[ speech quality ]] of the << converted singing voice >> is significantly degraded compared to that of a natural singing voice due to various factors , such as analysis and modeling errors in the vocoder-based framework .", "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": "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": "In this paper , we propose an [[ automatic estimation method ]] for << word significance -LRB- weights -RRB- >> based on its influence on IR .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Extensive experiments on two tasks have demonstrated the superiority of our [[ method ]] over the << state-of-the-art methods >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "We compare two language modelling toolkits , the CMU and the SRI toolkit and arrive at three results : 1 -RRB- [[ word-lemma based feature function models ]] produce better results than << token-based models >> , 2 -RRB- adding a PoS-tag feature function to the word-lemma model improves the output and 3 -RRB- weights for lexical translations are suitable if the training material is similar to the texts to be translated .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Experimental results are presented to compare [[ LNMF ]] with the << NMF and PCA methods >> for face representation and recognition , which demonstrates advantages of LNMF .", "aspect": "scii"}, {"sentiment": "COMPARE", "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": "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 present controlled experiments showing the << WSD accuracy >> of current typical SMT models to be significantly lower than [[ that ]] of all the dedicated WSD models considered .", "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": "We evaluate the << models >> on standard test sets , showing performance competitive with existing [[ methods ]] trained on hand prepared datasets .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Experiments with both synthetic and real data show that this new [[ algorithm ]] is faster , more accurate and more stable than existing << ones >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Since product analysis is a generalization of factor analysis , [[ product analysis ]] always finds a higher data likelihood than << factor analysis >> .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "The experimental results demonstrated that the annotation performance of this [[ method ]] outperforms some traditional << annotation methods >> by about 8 % in mean precision , showing a potential of the Maximum Entropy Model in the task of automatic image annotation .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "This mining procedure of AND and OR patterns is readily integrated to [[ boosting ]] , which improves the generalization ability over the conventional << boosting decision trees >> and boosting decision stumps .", "aspect": "scii"}, {"sentiment": "COMPARE", "sentence": "Contrary to existing [[ greedy techniques ]] , these << tasks >> are posed in the form of a discrete global optimization problem with a well defined objective function .", "aspect": "scii"}, {"sentiment": "COMPARE", "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": "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": "[[ It ]] also facilitates more efficient statistical ranking than a previous << approach >> to statistical generation .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "The issue of [[ system response ]] to users has been extensively studied by the << natural language generation community >> , though rarely in the context of dialog systems .", "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": "A deterministic parser is under development which represents a departure from traditional deterministic parsers in that << it >> combines both [[ symbolic and connectionist components ]] .", "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": "The << demonstrator >> embodies an interesting combination of [[ hand-built , symbolic resources ]] and stochastic processes .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "How to obtain [[ hierarchical relations ]] -LRB- e.g. superordinate - hyponym relation , synonym relation -RRB- is one of the most important problems for << thesaurus construction >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "It was implemented in the [[ IE module ]] of << FACILE , a EU project for multilingual text classification and IE >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "In the phase of training , a basic << visual vocabulary >> consisting of [[ blob-tokens ]] to describe the image content is generated at first ; then the statistical relationship is modeled between the blob-tokens and keywords by a Maximum Entropy Model constructed from the training set of labeled images .", "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": "With a sentence-aligned corpus , translation equivalences are suggested by analysing the [[ frequency profiles ]] of << parallel concordances >> .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "This paper solves the automatic initial-ization problem by performing boosted shape detection as a generic measurement process and integrating [[ it ]] in our << tracking framework >> .", "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": "The << board >> plugs directly into the VME bus of the SUN4 , which controls the system and contains the natural language system and [[ application back end ]] .", "aspect": "scii"}, {"sentiment": "PART-OF", "sentence": "<< CriterionSM Online Essay Evaluation Service >> includes a capability that labels sentences in student writing with [[ essay-based discourse elements ]] -LRB- e.g. , thesis statements -RRB- .", "aspect": "scii"}, {"sentiment": "PART-OF", "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": "PART-OF", "sentence": "We compare two language modelling toolkits , the CMU and the SRI toolkit and arrive at three results : 1 -RRB- word-lemma based feature function models produce better results than token-based models , 2 -RRB- adding a [[ PoS-tag feature function ]] to the << word-lemma model >> improves the output and 3 -RRB- weights for lexical translations are suitable if the training material is similar to the texts to be translated .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "In this paper we show how two standard outputs from information extraction -LRB- IE -RRB- systems - [[ named entity annotations ]] and << scenario templates >> - can be used to enhance access to text collections via a standard text browser .", "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": "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": "CONJUNCTION", "sentence": "Many computer vision applications , such as [[ image classification ]] and << video indexing >> , are usually multi-label classification problems in which an instance can be assigned to more than one category .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "We present two methods for capturing nonstationary chaos , then present a few examples including [[ biological signals ]] , << ocean waves >> and traffic flow .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "sentence": "In this paper , we present a digital signal processor -LRB- DSP -RRB- implementation of real-time statistical voice conversion -LRB- VC -RRB- for [[ silent speech enhancement ]] and << electrolaryngeal speech enhancement >> .", "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": "We use a [[ corpus of bracketed sentences ]] , called a Treebank , in combination with << decision tree building >> to tease out the relevant aspects of a parse tree that will determine the correct parse of a sentence .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "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": "CONJUNCTION", "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": "CONJUNCTION", "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": "CONJUNCTION", "sentence": "Robust natural language interpretation requires strong [[ semantic domain models ]] , << fail-soft recovery heuristics >> , and very flexible control structures .", "aspect": "scii"}, {"sentiment": "CONJUNCTION", "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": "CONJUNCTION", "sentence": "This paper discusses three research initiatives at PARC that exemplify these themes : a text-image editor -LSB- 1 -RSB- , a wordspotter for [[ voice editing and indexing ]] -LSB- 12 -RSB- , and a << decoding framework >> for scanned-document content retrieval -LSB- 4 -RSB- .", "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": "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"}]