Chinese Lexical Semantics 13th Workshop, CLSW 2012, Wuhan, China, July 6-8, 2012, Revised Selected Papers

• Main Authors: Ji, Donghong, Xiao, Guozheng
• Format: eBook
• Language: English
• Published: Netherlands Springer Nature 2013; Springer Berlin / Heidelberg; Springer
• Edition: 1
• Series: Lecture Notes in Computer Science
• Subjects: Chinese language; Chinese language-Semantics-Congresses; Computational linguistics; Special computer methods

This book constitutes carefully reviewed and revised selected papers from the 13th Chinese Lexical Semantics Workshop, CLSW 2012, held in Wuhan, China, in July 2012. The 67 full papers and 17 short papers presented in this volume were carefully reviewed and selected from 169 submissions. They are or...

Table of Contents:

• Automatic Update System -- Statistic Data and Application of Emotion Corpus -- Conclusion and Future Works -- References -- Termhood-Based Comparability Metrics of Comparable Corpus in Special Domain -- Introduction -- Related Works -- Building Comparable Corpus -- Comparability Metrics of Comparable Corpus -- Termhood-Based Comparability Metrics of ComparableCorpus -- The Basic Idea -- Key Technology in the Proposed Method -- Experiments and Result Analysis -- Data -- Data Processing -- Experiments and Results -- Evaluation -- Methods of Bilingual Term Extraction and Evaluation -- Results and Analysis -- Conclusions and Future Works -- References -- Corpus-Based Statistics of Pre-Qin Chinese -- Introduction -- Related Work -- Statistics of Characters in Pre-Qin Literatures -- High Frequency Characters and General Characters -- The Entropy of Pre-Qin Chinese Character -- Statistics of Words in Pre-Qin Literatures -- Distribution of Frequency -- Distribution of Word Length -- Distribution of Words' Part-of-Speech -- Conclusions and Future Work -- References -- Automatic Acquisition of Chinese Words' Property of Times -- Introduction -- Related Works -- The Corpus -- Quantification of Words' Property of Times Based on Frequency, TF-IDF and TF-IWF -- Quantification Based on Highest Frequency -- Quantification Based on TF-IDF -- Quantification Based on TF-IWF -- Automatic Acquisition of Words' Property of Times -- Naive Bayes -- Classification with Naive Bayes -- Conclusion and Further Works -- References -- A Study of English Word Sense Disambiguation Base on WordNet -- Introduction -- Related Researches and Basic Concepts -- The Introduction of WordNet -- The Introduction of MT -- The Introduction of Statistical Machine Translation -- Case Study on "Crack" -- Analysis of "Crack's" Senses and Word Classes
• Translation of the Contextual Meaning of "Crack" -- Translation of the Collocative Meaning of "Crack" -- Translation of Idiom of "Crack" -- Discussion and Conclusion -- References -- The Unified Platform for Language Monitoring Based on the Temporal-Spatial Model of Vocabulary Movement -- Introduction -- The Temporal-Spatial Model of Vocabulary Movement -- Definition of the Temporal-Spatial Model -- Calculation of the Model Quantities -- The Experiments of Vocabulary Monitoring -- The Experiments Corpus -- The Process of Experiments -- The Extraction of Various Types of Vocabulary -- Summary -- References -- Elementary Discourse Unit in Chinese Discourse Structure Analysis -- Introduction -- Chinese Elementary Discourse Units -- EDU is Single Sentence -- EDU is the Clause of Complex Sentence -- Punctuation and EDU -- Special Sentence Pattern Processing -- Automatic Identification of the Chinese EDUs -- Conclusion -- References -- A Corpus-Based Study of Epistemic Modality Markers in Chinese Research Articles -- Introduction -- Epistemic Modality Markers (EMMs) -- Research Design -- Research Questions -- Research Data -- Research Method -- Results and Discussions -- No Statistically Significant Differences of EMMs Cross-Disciplinarily -- Chinese Research Articles Much More Heavily Hedged in Comparison with those in Other Languages -- Functions of Hedging Strategies and Chinese Traditional Academic Culture -- Conclusion -- References -- Lexical Computation -- Rule-Based Computation of Semantic Orientation for Chinese Sentence -- Introduction -- Related Works -- Semantic Orientation and Its Main Properties -- Rule-Based Chinese Sentence SO Computation -- Processing Flow -- The Preparation of Dictionaries -- The Compilation and Application of Rules -- Experiment Results and Discussions -- Conclusion -- References
• Extracting Infrequent Product Features by Patterns -- Selecting Seed Product Features -- Creating the SBGSet Corpus for Extracting Patterns -- Extract Frequent Patterns -- Selecting and Scoring Patterns -- Extracting Product Features with Patterns -- Evaluation -- Experiment Setting -- Evaluation -- The Corpora -- Test Sets -- Results of Experiments -- Conclusion and Future Work -- References -- Ensemble Learning for Sentiment Classification -- Introduction -- Methodology -- Motivation -- Overview -- Base-Level Classification Algorithms -- Stacking -- Experiments -- Corpus -- Diversity among the Algorithms at Base-Level -- The Effect of Negation -- Stacking vs Voting -- The Effect of Opinion Summary -- Diversity Analysis -- Conclusion -- References -- Social Relation Extraction Based on Chinese Wikipedia Articles -- Introduction -- System Description -- Social Relation Extraction -- Relation Words Extraction -- Social Relation Information Extraction -- Experiment Results and Analysis -- Conclusions -- References -- Event Recognition Based on Co-occurrence Concept Analysis -- Introduction -- Related Work -- Creating Meta-event by Co-occurrence Analysis -- News Event Recognition Based on Markov Chain -- Experiment -- Conclusion -- References -- Corpus Linguistics -- Atomic Event Semantic Roles and Chinese Instances Analysis -- Introduction -- Event-Based Semantic Roles -- Core Semantic Roles -- Additional Semantic Roles -- Logical Operators -- Recursive Event -- Conclusions -- References -- Construction and Application of Chinese Emotional Corpus -- Introduction -- Corpus Design -- Versatility -- Descriptiveness -- Data Collecting -- Emotional Corpus Annotation System -- Annotation Based on TEI -- Emotion Annotation System -- Corpus Quality Control -- Annotation Criterion and Input System -- Artificial Calibration -- Mechanism for Correcting Errors
• Active Learning on Sentiment Classification by Selecting Both Words and Documents -- Introduction -- Related Work -- Sentiment Classification Method of Learning from Both Words and Documents -- Active Learning with Collaborative Selection on Both Words and Documents -- Annotation Costs -- Selection of Sentiment Words -- Sort of Word and Document Based on Weight -- Experiments -- Conclusion -- References -- Research on Intrinsic Plagiarism Detection Resolution: A Supervised Learning Approach -- Introduction -- Related Work -- Intrinsic Plagiarism Detection Framework -- System Framework -- Feature Selection -- Quantizing Feature -- Experimental Results -- Experiment Setting -- Evaluation Method -- Results and Analyses -- Conclusions and Future Work -- References -- Employing Emotion Keywords to Improve Cross-Domain Sentiment Classification -- Introduction -- Related Work -- Our Approach to Cross-Domain Sentiment Classification -- Framework Overview -- Gathering and Labeling the Emotion Keywords -- Automatically Labeling Samples in Target Domain -- Label-Propagation Algorithm Based on Bipartite Graph (LP) -- System Implementation Based on the Domain Adaptation Approach to Sentiment Classification with Emotion Keywords -- Experiments -- Experimental Setting -- Classification Result of Automatically-Labeled Samples in Target Domain -- Results of Our Approach to Cross-Domain Sentiment Classification -- Conclusions -- References -- Extracting Chinese Product Features: Representing a Sequence by a Set of Skip-Bigrams -- Introduction -- Related Work -- Representing a Word Sequence with a Set of Skip Bigrams -- A Set of Skip Bigrams -- The Conversion between a Sequence and a SBGSet -- Extracting Frequent Product Features -- Creating SBGSet Corpus -- Extracting Frequent Candidate Product Features -- Filtering Product Features
• Studies on Automatic Recognition of Contemporary Chinese Common Preposition Usage
• Intro -- Title -- Preface -- Organization -- Table of Contents -- Applications on Natural Language Processing -- MT-Oriented and Computer-Based Subject Restoration for Chinese Empty-Subject Sentences -- Introduction -- Mechanisms for Subject Ellipsis -- Stereotyped Expressions -- Principle of Economy -- Discourse Features -- Restoration of Empty Subjects -- ESS Identification -- Restoration and Tagging of ESS Empty Subjects (ES) -- Case Study -- Concluding Remarks -- References -- Incorporating Lexical Semantic Similarity to Tree Kernel-Based Chinese Relation Extraction -- Introduction -- Semantic Convolution Tree Kernel for RE -- Convolution Tree Kernel -- Semantic Convolution Tree Kernel -- Lexical Semantic Similarity Calculation -- Experimentation -- Experimental Setting -- Experimental Results and Analysis -- Conclusion and Future Work -- References -- Research on Chinese Sentence Compression for the Title Generation -- Introduction -- Previous Work -- Corpora -- Our Work -- Features -- Decoding -- Loss Function -- Evaluation -- Experiments -- Experimental Set-up -- Results -- Conclusion -- References -- Event Argument Extraction Based on CRF -- Introduction -- Related Work -- Motivation -- Solution -- Feature Selection -- Experiments -- Experiment Settings -- Results -- Problems Existing in the Experiments -- Conclusion -- References -- Fuzzy Matching for N-Gram-Based MT Evaluation -- Introduction -- Related Works -- BLEU -- Fuzzy Matching -- Fuzzy Matching for N-Grams -- WordNet-Based Lexical Similarity -- N-Gram Similarity -- Implementation Details of Fuzzy Matching in BLEU -- Experiment -- Evaluation with Fuzzy Matching -- Evaluation with Different N -- Effectiveness of WordNet in Fuzzy Matching -- Evaluation on Different Number of References -- Conclusion -- References