Natural Language Processing – IJCNLP 2004: First International Joint Conference, Hainan Island, China, March 22-24, 2004, Revised Selected Papers

Table of Contents......Page 12
Fast Reinforcement Learning of Dialogue Policies Using Stable Function Approximation......Page 20
Zero Pronoun Resolution Based on Automatically Constructed Case Frames and Structural Preference of Antecedents......Page 31
Improving Noun Phrase Coreference Resolution by Matching Strings......Page 41
Combining Labeled and Unlabeled Data for Learning Cross-Document Structural Relationships......Page 51
Parsing Mixed Constructions in a Type Feature Structure Grammar......Page 61
Iterative CKY Parsing for Probabilistic Context-Free Grammars......Page 71
Causal Relation Extraction Using Cue Phrase and Lexical Pair Probabilities......Page 80
A Re-examination of IR Techniques in QA System......Page 90
A Novel Pattern Learning Method for Open Domain Question Answering......Page 100
Chinese Named Entity Recognition Based on Multilevel Linguistic Features......Page 109
Information Flow Analysis with Chinese Text......Page 119
Phoneme-Based Transliteration of Foreign Names for OOV Problem......Page 129
Window-Based Method for Information Retrieval......Page 139
Improving Relevance Feedback in Language Modeling Approach: Maximum a Posteriori Probability Criterion and Three-Component Mixture Model......Page 149
BBS Based Hot Topic Retrieval Using Back-Propagation Neural Network......Page 158
How Effective Is Query Expansion for Finding Novel Information?......Page 168
The Hinoki Treebank. A Treebank for Text Understanding......Page 177
Building a Parallel Bilingual Syntactically Annotated Corpus......Page 187
Acquiring Bilingual Named Entity Translations from Content-Aligned Corpora......Page 196
Visual Semantics and Ontology of Eventive Verbs......Page 206
A Persistent Feature-Object Database for Intelligent Text Archive Systems......Page 216
Example-Based Machine Translation Without Saying Inferable Predicate......Page 225
Improving Back-Transliteration by Combining Information Sources......Page 235
Bilingual Sentence Alignment Based on Punctuation Statistics and Lexicon......Page 243
Automatic Learning of Parallel Dependency Treelet Pairs......Page 252
Practical Translation Pattern Acquisition from Combined Language Resources......Page 263
An English-Hindi Statistical Machine Translation System......Page 273
Robust Speaker Identification System Based on Wavelet Transform and Gaussian Mixture Model......Page 282
Selecting Prosody Parameters for Unit Selection Based Chinese TTS......Page 291
Natural Language Database Access Using Semi-automatically Constructed Translation Knowledge......Page 299
Korean Stochastic Word-Spacing with Dynamic Expansion of Candidate Words List......Page 309
You Don’t Have to Think Twice if You Carefully Tokenize......Page 318
Automatic Genre Detection of Web Documents......Page 329
Statistical Substring Reduction in Linear Time......Page 339
Detecting Sentence Boundaries in Japanese Speech Transcriptions Using a Morphological Analyzer......Page 347
Specification Retrieval – How to Find Attribute-Value Information on the Web......Page 357
Conceptual Information-Based Sense Disambiguation......Page 367
Influence of WSD on Cross-Language Information Retrieval......Page 377
Resolution of Modifier-Head Relation Gaps Using Automatically Extracted Metonymic Expressions......Page 386
Word Sense Disambiguation Using Heterogeneous Language Resources......Page 396
Improving Word Sense Disambiguation by Pseudo-samples......Page 405
Long Distance Dependency in Language Modeling: An Empirical Study......Page 415
Word Folding: Taking the Snapshot of Words Instead of the Whole......Page 425
Bilingual Chunk Alignment Based on Interactional Matching and Probabilistic Latent Semantic Indexing......Page 435
Learning to Filter Junk E-mail from Positive and Unlabeled Examples......Page 445
A Collaborative Ability Measurement for Co-training......Page 455
Flexible Margin Selection for Reranking with Full Pairwise Samples......Page 465
A Comparative Study on the Use of Labeled and Unlabeled Data for Large Margin Classifiers......Page 475
Comparing Entropies Within the Chinese Language......Page 485
NTPC: N-Fold Templated Piped Correction......Page 495
A Three Level Cache-Based Adaptive Chinese Language Model......Page 506
Using a Smoothing Maximum Entropy Model for Chinese Nominal Entity Tagging......Page 512
Deterministic Dependency Structure Analyzer for Chinese......Page 519
High Speed Unknown Word Prediction Using Support Vector Machine for Chinese Text-to-Speech Systems......Page 528
Syntactic Analysis of Long Sentences Based on S-Clauses......Page 537
Chinese Chunk Identification Using SVMs Plus Sigmoid......Page 546
Tagging Complex NEs with MaxEnt Models: Layered Structures Versus Extended Tagset......Page 556
A Nearest-Neighbor Method for Resolving PP-Attachment Ambiguity......Page 564
Detection of Incorrect Case Assignments in Paraphrase Generation......Page 574
Building a Pronominalization Model by Feature Selection and Machine Learning......Page 585
Categorizing Unknown Text Segments for Information Extraction Using a Search Result Mining Approach......Page 595
Mining Table Information on the Internet......Page 606
Collecting Evaluative Expressions for Opinion Extraction......Page 615
A Study of Semi-discrete Matrix Decomposition for LSI in Automated Text Categorization......Page 625
Systematic Construction of Hierarchical Classifier in SVM-Based Text Categorization......Page 635
Implementing the Syntax of Japanese Numeral Classifiers......Page 645
A Graph Grammar Approach to Map Between Dependency Trees and Topological Models......Page 655
The Automatic Acquisition of Verb Subcategorisations and Their Impact on the Performance of an HPSG Parser......Page 665
Chinese Treebanks and Grammar Extraction......Page 674
FML-Based SCF Predefinition Learning for Chinese Verbs......Page 683
Deep Analysis of Modern Greek......Page 693
Corpus-Oriented Grammar Development for Acquiring a Head-Driven Phrase Structure Grammar from the Penn Treebank......Page 703
Unsupervised Segmentation of Chinese Corpus Using Accessor Variety......Page 713
Chinese Unknown Word Identification Using Class-Based LM......Page 723
An Example-Based Study on Chinese Word Segmentation Using Critical Fragments......Page 733
The Use of SVM for Chinese New Word Identification......Page 742
Chinese New Word Finding Using Character-Based Parsing Model......Page 752
Introduction......Page 762
Spoken Versus Written Queries for Mobile Information Access: An Experiment on Mandarin Chinese......Page 764
An Interactive Proofreading System for Inappropriately Selected Words on Using Predictive Text Entry......Page 774
Dit4dah: Predictive Pruning for Morse Code Text Entry......Page 784
Introduction......Page 795
Unsupervised Event Extraction from Biomedical Literature Using Co-occurrence Information and Basic Patterns......Page 796
Annotation of Gene Products in the Literature with Gene Ontology Terms Using Syntactic Dependencies......Page 806
Mining Biomedical Abstracts: What’s in a Term?......Page 816
SVM-Based Biological Named Entity Recognition Using Minimum Edit-Distance Feature Boosted by Virtual Examples......Page 826
K......Page 834
T......Page 835
Z......Page 836