Natural language processing : IJCNLP 2004 : First International Joint Conference, Hainan Island, China, March 22-24, 2004 : revised selected papers

Dialogue and Discourse.- Fast Reinforcement Learning of Dialogue Policies Using Stable Function Approximation.- Zero Pronoun Resolution Based on Automatically Constructed Case Frames and Structural Preference of Antecedents.- Improving Noun Phrase Coreference Resolution by Matching Strings.- Combining Labeled and Unlabeled Data for Learning Cross-Document Structural Relationships.- FSA, Parsing Algorithms.- Parsing Mixed Constructions in a Type Feature Structure Grammar.- Iterative CKY Parsing for Probabilistic Context-Free Grammars.- Information Extraction and Question Answering.- Causal Relation Extraction Using Cue Phrase and Lexical Pair Probabilities.- A Re-examination of IR Techniques in QA System.- A Novel Pattern Learning Method for Open Domain Question Answering.- Chinese Named Entity Recognition Based on Multilevel Linguistic Features.- Information Retrieval.- Information Flow Analysis with Chinese Text.- Phoneme-Based Transliteration of Foreign Names for OOV Problem.- Window-Based Method for Information Retrieval.- Improving Relevance Feedback in Language Modeling Approach: Maximum a Posteriori Probability Criterion and Three-Component Mixture Model.- BBS Based Hot Topic Retrieval Using Back-Propagation Neural Network.- How Effective Is Query Expansion for Finding Novel Information?.- Lexical Semantics, Ontology and Linguistic Resources.- The Hinoki Treebank A Treebank for Text Understanding.- Building a Parallel Bilingual Syntactically Annotated Corpus.- Acquiring Bilingual Named Entity Translations from Content-Aligned Corpora.- Visual Semantics and Ontology of Eventive Verbs.- A Persistent Feature-Object Database for Intelligent Text Archive Systems.- Machine Translation and Multilinguality.- Example-Based Machine Translation Without Saying Inferable Predicate.- Improving Back-Transliteration by Combining Information Sources.- Bilingual Sentence Alignment Based on Punctuation Statistics and Lexicon.- Automatic Learning of Parallel Dependency Treelet Pairs.- Practical Translation Pattern Acquisition from Combined Language Resources.- An English-Hindi Statistical Machine Translation System.- NLP Software and Application.- Robust Speaker Identification System Based on Wavelet Transform and Gaussian Mixture Model.- Selecting Prosody Parameters for Unit Selection Based Chinese TTS.- Natural Language Database Access Using Semi-automatically Constructed Translation Knowledge.- Korean Stochastic Word-Spacing with Dynamic Expansion of Candidate Words List.- You Don't Have to Think Twice if You Carefully Tokenize.- Automatic Genre Detection of Web Documents.- Statistical Substring Reduction in Linear Time.- Detecting Sentence Boundaries in Japanese Speech Transcriptions Using a Morphological Analyzer.- Specification Retrieval - How to Find Attribute-Value Information on the Web.- Semantic Disambiguation.- Conceptual Information-Based Sense Disambiguation.- Influence of WSD on Cross-Language Information Retrieval.- Resolution of Modifier-Head Relation Gaps Using Automatically Extracted Metonymic Expressions.- Word Sense Disambiguation Using Heterogeneous Language Resources.- Improving Word Sense Disambiguation by Pseudo-samples.- Statistical Models and Machine Learning for NLP.- Long Distance Dependency in Language Modeling: An Empirical Study.- Word Folding: Taking the Snapshot of Words Instead of the Whole.- Bilingual Chunk Alignment Based on Interactional Matching and Probabilistic Latent Semantic Indexing.- Learning to Filter Junk E-Mail from Positive and Unlabeled Examples.- A Collaborative Ability Measurement for Co-training.- Flexible Margin Selection for Reranking with Full Pairwise Samples.- A Comparative Study on the Use of Labeled and Unlabeled Data for Large Margin Classifiers.- Comparing Entropies within the Chinese Language.- NTPC: N-fold Templated Piped Correction.- A Three Level Cache-Based Adaptive Chinese Language Model.- Taggers, Chunkers, Shallow Parsers.- Using a Smoothing Maximum Entropy Model for Chinese Nominal Entity Tagging.- Deterministic Dependency Structure Analyzer for Chinese.- High Speed Unknown Word Prediction Using Support Vector Machine for Chinese Text-to-Speech Systems.- Syntactic Analysis of Long Sentences Based on S-Clauses.- Chinese Chunk Identification Using SVMs Plus Sigmoid.- Tagging Complex NEs with MaxEnt Models: Layered Structures Versus Extended Tagset.- A Nearest-Neighbor Method for Resolving PP-Attachment Ambiguity.- Text and Sentence Generation.- Detection of Incorrect Case Assignments in Paraphrase Generation.- Building a Pronominalization Model by Feature Selection and Machine Learning.- Text Mining.- Categorizing Unknown Text Segments for Information Extraction Using a Search Result Mining Approach.- Mining Table Information on the Internet.- Collecting Evaluative Expressions for Opinion Extraction.- A Study of Semi-discrete Matrix Decomposition for LSI in Automated Text Categorization.- Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization.- Theories and Formalisms for Morphology, Syntax and Semantics.- Implementing the Syntax of Japanese Numeral Classifiers.- A Graph Grammar Approach to Map Between Dependency Trees and Topological Models.- The Automatic Acquisition of Verb Subcategorisations and Their Impact on the Performance of an HPSG Parser.- Chinese Treebanks and Grammar Extraction.- FML-Based SCF Predefinition Learning for Chinese Verbs.- Deep Analysis of Modern Greek.- Corpus-Oriented Grammar Development for Acquiring a Head-Driven Phrase Structure Grammar from the Penn Treebank.- Word Segmentation.- Unsupervised Segmentation of Chinese Corpus Using Accessor Variety.- Chinese Unknown Word Identification Using Class-Based LM.- An Example-Based Study on Chinese Word Segmentation Using Critical Fragments.- The Use of SVM for Chinese New Word Identification.- Chinese New Word Finding Using Character-Based Parsing Model.- Thematic Session: Natural Language Technology in Mobile Information Retrieval and Text Processing User Interfaces.- Thematic Session: Natural Language Technology in Mobile Information Retrieval and Text Processing User Interfaces.- Spoken Versus Written Queries for Mobile Information Access: An Experiment on Mandarin Chinese.- An Interactive Proofreading System for Inappropriately Selected Words on Using Predictive Text Entry.- Dit4dah: Predictive Pruning for Morse Code Text Entry.- Thematic Session: Text Mining in Biomedicine.- Thematic Session: Text Mining in Biomedicine.- Unsupervised Event Extraction from Biomedical Literature Using Co-occurrence Information and Basic Patterns.- Annotation of Gene Products in the Literature with Gene Ontology Terms Using Syntactic Dependencies.- Mining Biomedical Abstracts: What's in a Term?.- SVM-Based Biological Named Entity Recognition Using Minimum Edit-Distance Feature Boosted by Virtual Examples.