Computational Linguistics and Intelligent Text Processing: 8th International Conference, Cicling 2007, Mexico City, Mexico, February 18-24, 2007, Proc

ISBN-13: 9783540709381 / Angielski / Miękka / 2007 / 670 str.

Alexander Gelbukh

Opis

This book constitutes the refereed proceedings of the 8th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2007, held in Mexico City, Mexico in February 2007. The 53 revised full papers presented together with 3 invited papers cover all current issues in computational linguistics research and present intelligent text processing applications.

Spis treści

Computational Linguistics Research.- Integration of Linguistic Resources for Verb Classification: FrameNet Frame, WordNet Verb and Suggested Upper Merged Ontology.- French EuroWordNet Lexical Database Improvements.- Building a Large-Scale Commonsense Knowledge Base by Converting an Existing One in a Different Language.- Conquering Language: Using NLP on a Massive Scale to Build High Dimensional Language Models from the Web.- On Heads and Coordination in Valence Acquisition.- Chinese Terminology Extraction Using Window-Based Contextual Information.- Baby-Steps Towards Building a Spanglish Language Model.- Latent Variable Models for Causal Knowledge Acquisition.- Finite-State Technology as a Programming Environment.- Morphological Disambiguation of Turkish Text with Perceptron Algorithm.- Part-of-Speech Tagging Using Word Probability Based on Category Patterns.- Handling Conjunctions in Named Entities.- ANERsys: An Arabic Named Entity Recognition System Based on Maximum Entropy.- Applying Machine Learning to Chinese Entity Detection and Tracking.- Evaluation of an Automatic Extension of Temporal Expression Treatment to Catalan.- A Generalized Approach to Word Segmentation Using Maximum Length Descending Frequency and Entropy Rate.- Tagging Sentence Boundaries in Biomedical Literature.- Probabilistic Classifications with TBL.- The Non-associativity of Polarized Tree-Based Grammars.- Dependency Analysis of Clauses Using Parse Tree Kernels.- Unsupervised Method for Parsing Coordinated Base Noun Phrases.- Text Categorization for Improved Priors of Word Meaning.- Case-Sensitivity of Classifiers for WSD: Complex Systems Disambiguate Tough Words Better.- Word Clustering for Collocation-Based Word Sense Disambiguation.- Lexical Constellations and the Structure of Meaning: A Prototype Application to WSD.- Rule-Based Protein Term Identification with Help from Automatic Species Tagging.- Unsupervised Discrimination of Person Names in Web Contexts.- Learning for Semantic Parsing.- The Usefulness of Conceptual Representation for the Identification of Semantic Variability Expressions.- Characterizing Humour: An Exploration of Features in Humorous Texts.- Representing Emotions with Linguistic Acuity.- Intelligent Text Processing Applications.- An Evaluation of UNL Usability for High Quality Multilingualization and Projections for a Future UNL++ Language.- Transfer-Based MT from Spanish into Basque: Reusability, Standardization and Open Source.- Dependency-Based Chinese-English Statistical Machine Translation.- Asymmetric Hybrid Machine Translation for Languages with Scarce Resources.- CL-Guided Korean-English MT System for Scientific Papers.- Comparing and Integrating Alignment Template and Standard Phrase-Based Statistical Machine Translation.- Dependency Analysis and CBR to Bridge the Generation Gap in Template-Based NLG.- Experiments on Generating Questions About Facts.- Expert vs. Non-expert Tutoring: Dialogue Moves, Interaction Patterns and Multi-utterance Turns.- A Competitive Term Selection Method for Information Retrieval.- Incorporating Passage Feature Within Language Model Framework for Information Retrieval.- Enhancing Cross-Language Question Answering by Combining Multiple Question Translations.- The Negative Effect of Machine Translation on Cross–Lingual Question Answering.- Using Clustering Approaches to Open-Domain Question Answering.- A Little Known Fact Is ... Answering Other Questions Using Interest-Markers.- Adapting the JIRS Passage Retrieval System to the Arabic Language.- Using Question-Answer Pairs in Extractive Summarization of Email Conversations.- NEO-CORTEX: A Performant User-Oriented Multi-Document Summarization System.- Event-Based Summarization Using Time Features.- NLP-Based Curation of Bacterial Regulatory Networks.- Exploiting Category Information and Document Information to Improve Term Weighting for Text Categorization.- On the Impact of Lexical and Linguistic Features in Genre- and Domain-Based Categorization.- Clustering Narrow-Domain Short Texts by Using the Kullback-Leibler Distance.- A Mixed Trigrams Approach for Context Sensitive Spell Checking.- Combining Methods for Detecting and Correcting Semantic Hidden Errors in Arabic Texts.