Natural Language Processing – IJCNLP 2005: Second International Joint Conference, Jeju Island, Korea, October 11-13, 2005. Proceedings

Description

This book constitutes the thoroughly refereed proceedings of the Second International Joint Conference on Natural Language Processing, IJCNLP 2005, held in Jeju Island, Korea in October 2005. The 88 revised full papers presented in this volume were carefully reviewed and selected from 289 submissions. The papers are organized in topical sections on information retrieval, corpus-based parsing, Web mining, rule-based parsing, disambiguation, text mining, document analysis, ontology and thesaurus, relation extraction, text classification, transliteration, machine translation, question answering, morphological analysis, text summarization, named entity recognition, linguistic resources and tools, discourse analysis, semantic analysis NLP applications, tagging, language models, spoken language, and terminology mining. Front Matter....Pages - A New Method for Sentiment Classification in Text Retrieval....Pages 1-9 Topic Tracking Based on Linguistic Features....Pages 10-21 The Use of Monolingual Context Vectors for Missing Translations in Cross-Language Information Retrieval....Pages 22-33 Automatic Image Annotation Using Maximum Entropy Model....Pages 34-45 Corpus-Based Analysis of Japanese Relative Clause Constructions....Pages 46-57 Parsing Biomedical Literature....Pages 58-69 Parsing the Penn Chinese Treebank with Semantic Knowledge....Pages 70-81 Using a Partially Annotated Corpus to Build a Dependency Parser for Japanese....Pages 82-92 Entropy as an Indicator of Context Boundaries: An Experiment Using a Web Search Engine....Pages 93-105 Automatic Discovery of Attribute Words from Web Documents....Pages 106-118 Aligning Needles in a Haystack: Paraphrase Acquisition Across the Web....Pages 119-130 Confirmed Knowledge Acquisition Using Mails Posted to a Mailing List....Pages 131-142 Automatic Partial Parsing Rule Acquisition Using Decision Tree Induction....Pages 143-154 Chunking Using Conditional Random Fields in Korean Texts....Pages 155-164 High Efficiency Realization for a Wide-Coverage Unification Grammar....Pages 165-176 Linguistically-Motivated Grammar Extraction, Generalization and Adaptation....Pages 177-187 PP-Attachment Disambiguation Boosted by a Gigantic Volume of Unambiguous Examples....Pages 188-198 Adapting a Probabilistic Disambiguation Model of an HPSG Parser to a New Domain....Pages 199-210 A Hybrid Approach to Single and Multiple PP Attachment Using WordNet....Pages 211-222 Period Disambiguation with Maxent Model....Pages 223-232 Acquiring Synonyms from Monolingual Comparable Texts....Pages 233-244 A Method of Recognizing Entity and Relation....Pages 245-256 Inversion Transduction Grammar Constraints for Mining Parallel Sentences from Quasi-Comparable Corpora....Pages 257-268 Automatic Term Extraction Based on Perplexity of Compound Words....Pages 269-279 Document Clustering with Grouping and Chaining Algorithms....Pages 280-291 Using Multiple Discriminant Analysis Approach for Linear Text Segmentation....Pages 292-301 Classifying Chinese Texts in Two Steps....Pages 302-313 Assigning Polarity Scores to Reviews Using Machine Learning Techniques....Pages 314-325 Analogy as Functional Recategorization: Abstraction with HowNet Semantics....Pages 326-333 PLSI Utilization for Automatic Thesaurus Construction....Pages 334-345 Analysis of an Iterative Algorithm for Term-Based Ontology Alignment....Pages 346-356 Finding Taxonomical Relation from an MRD for Thesaurus Extension....Pages 357-365 Relation Extraction Using Support Vector Machine....Pages 366-377 Discovering Relations Between Named Entities from a Large Raw Corpus Using Tree Similarity-Based Clustering....Pages 378-389 Automatic Relation Extraction with Model Order Selection and Discriminative Label Identification....Pages 390-401 Mining Inter-Entity Semantic Relations Using Improved Transductive Learning....Pages 402-413 A Preliminary Work on Classifying Time Granularities of Temporal Questions....Pages 414-425 Classification of Multiple-Sentence Questions....Pages 426-437 A Rule Based Syllabification Algorithm for Sinhala....Pages 438-449 An Ensemble of Grapheme and Phoneme for Machine Transliteration....Pages 450-461 Improving Statistical Word Alignment with Ensemble Methods....Pages 462-473 Empirical Study of Utilizing Morph-Syntactic Information in SMT....Pages 474-485 Instance-Based Generation for Interactive Restricted Domain Question Answering Systems....Pages 486-497 Answering Definition Questions Using Web Knowledge Bases....Pages 498-506 Exploring Syntactic Relation Patterns for Question Answering....Pages 507-518 Web-Based Unsupervised Learning for Query Formulation in Question Answering....Pages 519-529 A Chunking Strategy Towards Unknown Word Detection in Chinese Word Segmentation....Pages 530-541 A Lexicon-Constrained Character Model for Chinese Morphological Analysis....Pages 542-552 Relative Compositionality of Multi-word Expressions: A Study of Verb-Noun (V-N) Collocations....Pages 553-564 Automatic Extraction of Fixed Multiword Expressions....Pages 565-575 Phrase-Based Statistical Machine Translation: A Level of Detail Approach....Pages 576-587 Why Is Zero Marking Important in Korean?....Pages 588-599 A Phrase-Based Context-Dependent Joint Probability Model for Named Entity Translation....Pages 600-611 Machine Translation Based on Constraint-Based Synchronous Grammar....Pages 612-623 A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation....Pages 624-635 Significant Sentence Extraction by Euclidean Distance Based on Singular Value Decomposition....Pages 636-645 Two-Phase Biomedical Named Entity Recognition Using A Hybrid Method....Pages 646-657 Heuristic Methods for Reducing Errors of Geographic Named Entities Learned by Bootstrapping....Pages 658-669 Building a Japanese-Chinese Dictionary Using Kanji/Hanzi Conversion....Pages 670-681 Automatic Acquisition of Basic Katakana Lexicon from a Given Corpus....Pages 682-693 CTEMP: A Chinese Temporal Parser for Extracting and Normalizing Temporal Information....Pages 694-706 French-English Terminology Extraction from Comparable Corpora....Pages 707-718 A Twin-Candidate Model of Coreference Resolution with Non-Anaphor Identification Capability....Pages 719-730 Improving Korean Speech Acts Analysis by Using Shrinkage and Discourse Stack....Pages 731-741 Anaphora Resolution for Biomedical Literature by Exploiting Multiple Resources....Pages 742-753 Automatic Slide Generation Based on Discourse Structure Analysis....Pages 754-766 Using the Structure of a Conceptual Network in Computing Semantic Relatedness....Pages 767-778 Semantic Role Labelling of Prepositional Phrases....Pages 779-791 Global Path-Based Refinement of Noisy Graphs Applied to Verb Semantics....Pages 792-803 Semantic Role Tagging for Chinese at the Lexical Level....Pages 804-814 Detecting Article Errors Based on the Mass Count Distinction....Pages 815-826 Principles of Non-stationary Hidden Markov Model and Its Applications to Sequence Labeling Task....Pages 827-837 Integrating Punctuation Rules and Naïve Bayesian Model for Chinese Creation Title Recognition....Pages 838-848 A Connectionist Model of Anticipation in Visual Worlds....Pages 849-861 Automatically Inducing a Part-of-Speech Tagger by Projecting from Multiple Source Languages Across Aligned Corpora....Pages 862-873 The Verbal Entries and Their Description in a Grammatical Information-Dictionary of Contemporary Tibetan....Pages 874-884 Tense Tagging for Verbs in Cross-Lingual Context: A Case Study....Pages 885-895 Regularisation Techniques for Conditional Random Fields: Parameterised Versus Parameter-Free....Pages 896-907 Exploiting Lexical Conceptual Structure for Paraphrase Generation....Pages 908-919 Word Sense Disambiguation by Relative Selection....Pages 920-932 Towards Robust High Performance Word Sense Disambiguation of English Verbs Using Rich Linguistic Features....Pages 933-944 Automatic Interpretation of Noun Compounds Using WordNet Similarity....Pages 945-956 An Empirical Study on Language Model Adaptation Using a Metric of Domain Similarity....Pages 957-968 A Comparative Study of Language Models for Book and Author Recognition....Pages 969-980 Lexical Choice via Topic Adaptation for Paraphrasing Written Language to Spoken Language....Pages 981-992 A Case-Based Reasoning Approach for Speech Corpus Generation....Pages 993-1003 Web-Based Terminology Translation Mining....Pages 1004-1016 Extracting Terminologically Relevant Collocations in the Translation of Chinese Monograph....Pages 1017-1028 Back Matter....Pages -