Information Retrieval/Document Classification/QA/ Summarization I -- Answering Contextual Questions Based on the Cohesion with Knowledge -- Segmentation of Mixed Chinese/English Document Including Scattered Italic Characters -- Using Pointwise Mutual Information to Identify Implicit Features in Customer Reviews -- Using Semi-supervised Learning for Question Classification -- Query Similarity Computing Based on System Similarity Measurement -- Machine Translation I -- An Improved Method for Finding Bilingual Collocation Correspondences from Monolingual Corpora -- A Syntactic Transformation Model for Statistical Machine Translation -- Word Alignment Between Chinese and Japanese Using Maximum Weight Matching on Bipartite Graph -- Improving Machine Transliteration Performance by Using Multiple Transliteration Models -- Information Retrieval/Document Classification/ QA/Summarization II -- Clique Percolation Method for Finding Naturally Cohesive and Overlapping Document Clusters -- Hybrid Approach to Extracting Information from Web-Tables -- A Novel Hierarchical Document Clustering Algorithm Based on a kNN Connection Graph -- Poster Session 1 -- The Great Importance of Cross-Document Relationships for Multi-document Summarization -- The Effects of Computer Assisted Instruction to Train People with Reading Disabilities Recognizing Chinese Characters -- Discrimination-Based Feature Selection for Multinomial Naïve Bayes Text Classification -- A Comparative Study on Chinese Word Clustering -- Populating FrameNet with Chinese Verbs Mapping Bilingual Ontological WordNet with FrameNet -- Collecting Novel Technical Terms from the Web by Estimating Domain Specificity of a Term -- Building Document Graphs for Multiple News Articles Summarization: An Event-Based Approach -- A Probabilistic Feature Based Maximum Entropy Model for Chinese Named Entity Recognition -- Correcting Bound Document Images Based on Automatic and Robust Curved Text Lines Estimation -- Cluster-Based Patent Retrieval Using International Patent Classification System -- Word Error Correction of Continuous Speech Recognition Using WEB Documents for Spoken Document Indexing -- Extracting English-Korean Transliteration Pairs from Web Corpora -- Word Segmentation/Chunking/Abbreviation Expansion/Writing-System Issues -- From Phoneme to Morpheme: Another Verification Using a Corpus -- Chinese Abbreviation Identification Using Abbreviation-Template Features and Context Information -- Word Frequency Approximation for Chinese Using Raw, MM-Segmented and Manually Segmented Corpora -- Identification of Maximal-Length Noun Phrases Based on Expanded Chunks and Classified Punctuations in Chinese -- A Hybrid Approach to Chinese Abbreviation Expansion -- Category-Pattern-Based Korean Word-Spacing -- An Integrated Approach to Chinese Word Segmentation and Part-of-Speech Tagging -- Kansuke: A Kanji Look-Up System Based on a Few Stroke Prototypes -- Modelling the Orthographic Neighbourhood for Japanese Kanji -- Reconstructing the Correct Writing Sequence from a Set of Chinese Character Strokes -- Machine Translation II -- Expansion of Machine Translation Bilingual Dictionaries by Using Existing Dictionaries and Thesauruses -- Feature Rich Translation Model for Example-Based Machine Translation -- Dictionaries for English-Vietnamese Machine Translation -- Poster Session 2 -- Translation Selection Through Machine Learning with Language Resources -- Acquiring Translational Equivalence from a Japanese-Chinese Parallel Corpus -- Deep Processing of Korean Floating Quantifier Constructions -- Compilation of a Dictionary of Japanese Functional Expressions with Hierarchical Organization -- A System to Indicate Honorific Misuse in Spoken Japanese -- A Chinese Corpus with Word Sense Annotation -- Multilingual Machine Translation of Closed Captions for Digital Television with Dynamic Dictionary Adaptation -- Acquiring Concept Hierarchies of Adjectives from Corpora -- Pronunciation Similarity Estimation for Spoken Language Learning -- A Novel Method for Rapid Speaker Adaptation Using Reference Support Speaker Selection -- Using Latent Semantics for NE Translation -- Chinese Chunking with Tri-training Learning -- Binarization Approaches to Email Categorization -- Investigating Problems of Semi-supervised Learning for Word Sense Disambiguation -- Developing a Dialog System for New Idea Generation Support -- Parsing/Semantics/Lexical Resources -- The Incremental Use of Morphological Information and Lexicalization in Data-Driven Dependency Parsing -- Pattern Dictionary Development Based on Non-compositional Language Model for Japanese Compound and Complex Sentences -- A Case-Based Reasoning Approach to Zero Anaphora Resolution in Chinese Texts -- Building a Collocation Net.