Sentence Compression for Target-Polarity Word Collocation Extraction
Published 1 August 2014
Yanyan Zhao, Wanxiang Che, Honglei Guo, Bing Qin, Zhong Su, Ting Liu
Citations12
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work applies a discriminative conditional random field model, with some special sentimentrelated features, in order to automatically compress sentiment sentences.
Abstract
Target-polarity word (T-P) collocation extraction, a basic sentiment analysis task, relies primarily on syntactic features to identify the relationships between targets and polarity words. A major problem of current research is that this task focuses on customer reviews, which are natural or spontaneous, thus posing a challenge to syntactic parsers. We address this problem by proposing a framework of adding a sentiment sentence compression (Sent Comp) step before performing T-P collocation extraction. Sent Comp seeks to remove the unnecessary information for senti-ment analysis, thereby compressing a complicated sentence into one that is shorter and easier to parse. We apply a discriminative conditional random field model, with some special sentiment-related features, in order to automatically compress sentiment sentences. Experiments show that Sent Comp significantly improves the performance of T-P collocation extraction. 1
Keywords
Computer Science
An Introduction to the Bootstrap
39,744 Citations1994Bradley Efron, Robert Tibshirani
Mining and summarizing customer reviews
7,714 Citations2004Minqing Hu, Bing Liu
This research aims to mine and to summarize all the customer reviews of a product, and proposes several novel techniques to perform these tasks.
now publishers, Inc. eBooksOpinion Mining and Sentiment Analysis
6,745 Citations2008Bo Pang, Lillian Lee
Encyclopedia of Machine Learning and Data MiningSentiment Analysis and Opinion Mining
3,319 Citations2017Lei Zhang, Bing Liu
Class-based n -gram models of natural language
2,893 Citations1992Peter F. Brown, P.V. deSouza +3 more
This work addresses the problem of predicting a word from previous words in a sample of text and discusses n-gram models based on classes of words, finding that these models are able to extract classes that have the flavor of either syntactically based groupings or semanticallybased groupings, depending on the nature of the underlying statistics.
Computational LinguisticsOpinion Word Expansion and Target Extraction through Double Propagation
1,100 Citations2011Guang Qiu, Bing Liu +2 more
This article study two important problems, namely, opinion lexicon expansion and opinion target extraction, and proposes a method based on bootstrapping that outperforms these existing methods significantly.
ACM Transactions on Information SystemsSentiment analysis in multiple languages
894 Citations2008Ahmed Abbasi, Hsinchun Chen +1 more
Stylistic features significantly enhanced performance across all testbeds while EWGA also outperformed other feature selection methods, indicating the utility of these features and techniques for document-level classification of sentiments.
Artificial IntelligenceSummarization beyond sentence extraction: A probabilistic approach to sentence compression
490 Citations2002Kevin Knight, Daniel Marcu
This paper focuses on sentence compression, a simpler version of this larger challenge, and aims to achieve two goals simultaneously: the authors' compressions should be grammatical, and they should retain the most important pieces of information.
RECERCAT (Consorci de Serveis Universitaris de Catalunya)Simple Semi-supervised Dependency Parsing
444 Citations2008Terry Koo, Xavier Carreras +1 more
This work focuses on the problem of lexical representation, introducing features that incorporate word clusters derived from a large unannotated corpus, and shows that the cluster-based features yield substantial gains in performance across a wide range of conditions.
LTP: A Chinese Language Technology Platform
401 Citations2010Wanxiang Che, Zhenghua Li +1 more
LTP (Language Technology Platform) is an integrated Chinese processing platform which includes a suite of high performance natural language processing modules and relevant corpora that achieved good results in some relevant evaluations, such as CoNLL and SemEval.
Journal of Artificial Intelligence ResearchGlobal Inference for Sentence Compression: An Integer Linear Programming Approach
316 Citations2008James Clarke, Mirella Lapata
This work shows how previous formulations of sentence compression can be recast as ILPs and extend these models with novel global constraints to infer globally optimal compressions in the presence of linguistically motivated constraints.
DSpace@MIT (Massachusetts Institute of Technology)Semi-Supervised Learning for Natural Language
304 Citations2005Percy Liang
This thesis focuses on two segmentation tasks, named-entity recognition and Chinese word segmentation, and shows that features derived from unlabeled data substantially improves performance, both in terms of reducing the amount of labeled data needed to achieve a certain performance level and in termsof reducing the error using a fixed amount of labeling data.
Sentence reduction for automatic text summarization
284 Citations2000Hongyan Jing
A novel sentence reduction system for automatically removing extraneous phrases from sentences that are extracted from a document for summarization purpose using multiple sources of knowledge, including syntactic knowledge, context information, and statistics computed from a corpus which consists of examples written by human professionals.
Name Tagging with Word Clusters and Discriminative Training
270 Citations2004S.L. Miller, Jethran Guinness +1 more
A technique for augmenting annotated training data with hierarchical word clusters that are automatically derived from a large unannotated corpus that achieves a 25% reduction in error over the state-of-the-art HMM trained on the same material.
Edinburgh Research Explorer (University of Edinburgh)Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming
218 Citations2011Kristian Woodsend, Mirella Lapata
A data-driven model based on quasi-synchronous grammar, a formalism that can naturally capture structural mismatches and complex rewrite operations, is presented and it is shown experimentally that the method creates simplifications that significantly reduce the reading difficulty of the input, while maintaining grammaticality and preserving its meaning.
Efficient, Feature-based, Conditional Random Field Parsing
180 Citations2008Jenny Rose Finkel, Alex Kleeman +1 more
This work presents the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data, and achieves state-of-the-art results.
Conference of the European Chapter of the Association for Computational LinguisticsDiscriminative Sentence Compression with Soft Syntactic Evidence
163 Citations2006Ryan McDonald
A model for sentence compression that uses a discriminative largemargin learning framework coupled with a novel feature set defined on compressed bigrams as well as deep syntactic representations provided by auxiliary dependency and phrase-structure parsers is presented.
Journal of Artificial Intelligence ResearchSentence Compression as Tree Transduction
157 Citations2009Timothy A. Cohn, Mirella Lapata
This paper presents a tree-to-tree transduction method for sentence compression based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can naturally capture structural mismatches.
Supervised and unsupervised learning for sentence compression
156 Citations2005Jenine Turner, Eugene Charniak
In addition to improving the original K&M noisy-channel model, unsupervised and semi-supervised models of the task are created to point out problems with modeling the task in this way.
Decision Support SystemsFeature selection for sentiment analysis based on content and syntax models
155 Citations2012Adnan Duric, Fei Song
A set of new feature selection schemes that use a Content and Syntax model to automatically learn a set of features in a review document by separating the entities that are being reviewed from the subjective expressions that describe those entities in terms of polarities are proposed.
Sentence Simplification for Semantic Role Labeling
112 Citations2008David Vickrey, Daphne Koller
A general method for learning how to iteratively simplify a sentence, thus decomposing complicated syntax into small, easy-to-process pieces and achieving near-state-of-the-art performance across syntactic variation.
Extracting Appraisal Expressions
110 Citations2007K R Bloom, Navendu Garg +1 more
It is suggested here that appraisal expression extraction should be viewed as a fundamental task in sentiment analysis and a system for effectively extracting and disambiguating adjectival appraisal expressions in English outputting a generic representation in terms of their evaluative function in the text is described.
Lexicalized Markov Grammars for Sentence Compression
104 Citations2007Kathleen McKeown, Michel Galley
A headdriven Markovization formulation of SCFG deletion rules is defined, which allows us to lexicalize probabilities of constituent deletions, and a robust approach for tree-to-tree alignment between arbitrary document-abstract parallel corpora is used.
Named Entity Recognition with Bilingual Constraints
90 Citations2013Wanxiang Che, Mengqiu Wang +2 more
A method is proposed that formulates the problem of exploring signals on unannotated bilingual text as a simple Integer Linear Program, which encourages entity tags to agree via bilingual constraints and can improve strong baselines for both Chinese and English.
Mining Opinion Words and Opinion Targets in a Two-Stage Framework
87 Citations2013Liheng Xu, Kang Liu +3 more
This paper proposes a novel two-stage method for mining opinion words and opinion targets, which naturally incorporates syntactic patterns in a Sentiment Graph to extract opinion word/target candidates and adopts a self-learning strategy to refine the results.
Document Summarization via Guided Sentence Compression
69 Citations2013Chen Li, Fei Liu +2 more
The results on the TAC 2008 and 2011 summarization data sets show that by incorporating the guided sentence compression model, the summarization system can yield significant performance gain as compared to the state-of-the-art.
Entity-Focused Sentence Simplification for Relation Extraction
57 Citations2010Makoto Miwa, Rune Sætre +2 more
A rule-based method to remove the information that is unnecessary for relation extraction from protein-protein interaction corpora using a dozen simple rules defined on output from a deep parser.
An extractive supervised two-stage method for sentence compression
55 Citations2010Dimitrios Galanis, Ion Androutsopoulos
A new method that compresses sentences by removing words using a Maximum Entropy classifier and chooses the best among the candidate compressions using a Support Vector Machine Regression model.
Sentence Compression with Joint Structural Inference
38 Citations2013Kapil Thadani, Kathleen McKeown
This work presents a novel approach for discriminative sentence compression that unifies these notions and jointly produces sequential and syntactic representations for output text, leveraging a compact integer linear programming formulation to maintain structural integrity.
Information Processing & ManagementDiscriminative sentence compression with conditional random fields
34 Citations2007Tadashi Nomoto
This paper devise several features for Conditional Random Fields that allow it to incorporate information on nonlinear relations among words and address the issue of data paucity by collecting data from RSS feeds available on the Internet, and turning them into training data for use with CRF.
ACM Transactions on Intelligent Systems and TechnologyAn abstractive approach to sentence compression
29 Citations2013Trevor Cohn, Mirella Lapata
This article creates a new corpus that is suited to the abstractive compression task and forms a discriminative tree-to-tree transduction model that can account for structural and lexical mismatches.