Computational Linguistics Research -- Integrating Semantic Frames from Multiple Sources -- Making Senses: Bootstrapping Sense-Tagged Lists of Semantically-Related Words -- Enriching Wordnets with New Relations and with Event and Argument Structures -- Experiments in Cross-Language Morphological Annotation Transfer -- Sentence Segmentation Model to Improve Tree Annotation Tool -- Markov Cluster Shortest Path Founded Upon the Alibi-Breaking Algorithm -- Unsupervised Learning of Verb Argument Structures -- A Methodology for Extracting Ontological Knowledge from Spanish Documents -- Automatically Determining Allowable Combinations of a Class of Flexible Multiword Expressions -- Web-Based Measurements of Intra-collocational Cohesion in Oxford Collocations Dictionary -- Probabilistic Neural Network Based English-Arabic Sentence Alignment -- Towards the Automatic Lemmatization of 16th Century Mexican Spanish: A Stemming Scheme for the CHEM -- Word Frequency Approximation for Chinese Without Using Manually-Annotated Corpus -- Abbreviation Recognition with MaxEnt Model -- An Efficient Multi-agent System Combining POS-Taggers for Arabic Texts -- A Comparative Evaluation of a New Unsupervised Sentence Boundary Detection Approach on Documents in English and Portuguese -- A General and Multi-lingual Phrase Chunking Model Based on Masking Method -- UCSG Shallow Parser -- Evaluating the Performance of the Survey Parser with the NIST Scheme -- Sequences of Part of Speech Tags vs. Sequences of Phrase Labels: How Do They Help in Parsing? -- Verb Sense Disambiguation Using Support Vector Machines: Impact of WordNet-Extracted Features -- Preposition Senses: Generalized Disambiguation Model -- An Unsupervised Language Independent Method of Name Discrimination Using Second Order Co-occurrence Features -- Extracting Key Phrases to Disambiguate Personal Names on the Web -- Chinese Noun Phrase Metaphor Recognition with Maximum Entropy Approach -- Zero Anaphora Resolution in Chinese Discourse -- Random Walks on Text Structures -- Shallow Case Role Annotation Using Two-Stage Feature-Enhanced String Matching -- SPARTE, a Test Suite for Recognising Textual Entailment in Spanish -- Analysis of a Textual Entailer -- Referring Via Document Parts -- Generation of Natural Language Explanations of Rules in an Expert System -- Generating a Set of Rules to Determine Honorific Expression Using Decision Tree Learning -- NLP (Natural Language Processing) for NLP (Natural Language Programming) -- Balancing Transactions in Practical Dialogues -- Finite State Grammar Transduction from Distributed Collected Knowledge -- Predicting Dialogue Acts from Prosodic Information -- Disambiguation Based on Wordnet for Transliteration of Arabic Numerals for Korean TTS -- Intelligent Text Processing Applications -- MFCRank: A Web Ranking Algorithm Based on Correlation of Multiple Features -- On Text Ranking for Information Retrieval Based on Degree of Preference -- Lexical Normalization and Relationship Alternatives for a Term Dependence Model in Information Retrieval -- Web Search Model for Dynamic and Fuzzy Directory Search -- Information Retrieval from Spoken Documents -- Automatic Image Annotation Based on WordNet and Hierarchical Ensembles -- Creating a Testbed for the Evaluation of Automatically Generated Back-of-the-Book Indexes -- Automatic Acquisition of Semantic-Based Question Reformulations for Question Answering -- Using N-Gram Models to Combine Query Translations in Cross-Language Question Answering -- A Question Answering System on Special Domain and the Implementation of Speech Interface -- Multi-document Summarization Based on BE-Vector Clustering -- Deriving Event Relevance from the Ontology Constructed with Formal Concept Analysis -- A Sentence Compression Module for Machine-Assisted Subtitling -- Application of Semi-supervised Learning to Evaluative Expression Classification -- A New Algorithm for Fast Discovery of Maximal Sequential Patterns in a Document Collection -- A Machine Learning Based Approach for Separating Head from Body in Web-Tables -- Clustering Abstracts of Scientific Texts Using the Transition Point Technique -- Sense Cluster Based Categorization and Clustering of Abstracts -- Analysing Part-of-Speech for Portuguese Text Classification -- Improving kNN Text Categorization by Removing Outliers from Training Set -- Writing for Language-Impaired Readers -- Document Copy Detection System Based on Plagiarism Patterns -- Regional vs. Global Robust Spelling Correction.