CICLing 2005 (www.CICLing.org) was the 6th Annual Conference on Intelligent Text Processing and Computational Linguistics. It was intended to provide a balanced view of the cutting-edge developments in both the theoretical foundations of computational linguistics and the practice of natural-language text processing with its numerous applications. A feature of CICLing conferences is their wide scope that covers nearly all areas of computational linguistics and all aspects of natural language processing applications. This year we were honored by the presence of our keynote speakers Christian Boitet (CLIPS-IMAG, Grenoble), Kevin Knight (ISI), Daniel Marcu (ISI), and Ellen Riloff (University of Utah), who delivered excellent extended lectures and organized vivid discussions and encouraging tutorials; their invited papers are published in this volume. Of 151 submissions received, 88 were selected for presentation; 53 as full papers and 35 as short papers, by exactly 200 authors from 26 countries: USA (15 papers); Mexico (12); China (9.5); Spain (7.5); South Korea (5.5); Singapore (5); Germany (4.8); Japan (4); UK (3.5); France (3.3); India (3); Italy (3); Czech Republic (2.5); Romania (2.3); Brazil, Canada, Greece, Ireland, Israel, the Netherlands, Norway, Portugal, Sweden, Switzerland (1 each); Hong Kong (0.5); and Russia (0.5) including the invited papers. Internationally co-authored papers are counted in equal fractions.
Inhalt
Computational Linguistics Research.- An Overview of Probabilistic Tree Transducers for Natural Language Processing.- A Modular Account of Information Structure in Extensible Dependency Grammar.- Modelling Grammatical and Lexical Knowledge: A Declarative Approach.- Constructing a Parser for Latin.- Parsing Korean Case Phenomena in a Type-Feature Structure Grammar.- A Computational Model of the Spanish Clitic System.- A Parallel Approach to Syllabification.- Towards Developing Probabilistic Generative Models for Reasoning with Natural Language Representations.- Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing.- Assigning Function Tags with a Simple Model.- Finding Discourse Relations in Student Essays.- Regional Versus Global Finite-State Error Repair.- Lexicalized Beam Thresholding Parsing with Prior and Boundary Estimates.- Unsupervised Evaluation of Parser Robustness.- Mutual Information Independence Model Using Kernel Density Estimation for Segmenting and Labeling Sequential Data.- Applying Conditional Random Fields to Chinese Shallow Parsing.- Distributional Thesaurus Versus WordNet: A Comparison of Backoff Techniques for Unsupervised PP Attachment.- Automatic Recognition of Czech Derivational Prefixes.- Korma 2003: Newly Improved Korean Morpheme Analysis Module for Reducing Terminological and Spacing Errors in Document Analysis.- Word Extraction Based on Semantic Constraints in Chinese Word-Formation.- Using Directed Graph Based BDMM Algorithm for Chinese Word Segmentation.- Entity-Based Noun Phrase Coreference Resolution.- The Right Frontier Constraint as Conditional.- Name Discrimination by Clustering Similar Contexts.- Word Sense Disambiguation by Semi-supervised Learning.- Crossing Parallel Corpora and Multilingual Lexical Databases for WSD.- A Mapping Between Classifiers and Training Conditions for WSD.- Multiwords and Word Sense Disambiguation.- Context Expansion with Global Keywords for a Conceptual Density-Based WSD.- Two Web-Based Approaches for Noun Sense Disambiguation.- Finding Instance Names and Alternative Glosses on the Web: WordNet Reloaded.- Automatic Synonym Acquisition Based on Matching of Definition Sentences in Multiple Dictionaries.- Enriching WordNet with Derivational Subnets.- Customisable Semantic Analysis of Texts.- ITOLDU, a Web Service to Pool Technical Lexical Terms in a Learning Environment and Contribute to Multilingual Lexical Databases.- Building a Situation-Based Language Knowledge Base.- Unsupervised Learning of P NP P Word Combinations.- Evaluating Evaluation Methods for Generation in the Presence of Variation.- Reconciling Parameterization, Configurability and Optimality in Natural Language Generation via Multiparadigm Programming.- Message Automata for Messages with Variants, and Methods for Their Translation.- The UNL Initiative: An Overview.- Interactive Resolution of Intrinsic and Translational Ambiguity in a Machine Translation System.- Chinese-Japanese Clause Alignment.- Direct Combination of Spelling and Pronunciation Information for Robust Back-Transliteration.- A Prosodic Diphone Database for Korean Text-to-Speech Synthesis System.- On a Pitch Detection Method Using Noise Reduction.- Toward Acoustic Models for Languages with Limited Linguistic Resources.- A Study on Pitch Detection in Time-Frequency Hybrid Domain.- VoiceUNL: A Semantic Representation of Emotions Within Universal Networking Language Formalism Based on a Dialogue Corpus Analysis.- Combining Multiple Statistical Classifiers to Improve the Accuracy of Task Classification.- A Finite State Network for Phonetic Text Processing.- Language Documentation: The Nahuatl Grammar.- Intelligent Text Processing Applications.- Creating Subjective and Objective Sentence Classifiers from Unannotated Texts.- Instance Pruning by Filtering Uninformative Words: An Information Extraction Case Study.- Incremental Information Extraction Using Tree-Based Context Representations.- Learning Information Extraction Rules for Protein Annotation from Unannotated Corpora.- Transformation-Based Information Extraction Using Learned Meta-rules.- A Machine Learning Approach to Information Extraction.- Automatic Time Expression Labeling for English and Chinese Text.- Integrating Natural Language Techniques in OO-Method.- Document Re-ordering Based on Key Terms in Top Retrieved Documents.- Merging Case Relations into VSM to Improve Information Retrieval Precision.- Evaluating Document-to-Document Relevance Based on Document Language Model: Modeling, Implementation and Performance Evaluation.- Retrieval Efficiency of Normalized Query Expansion.- Selecting Interesting Articles Using Their Similarity Based Only on Positive Examples.- Question Classification in Spanish and Portuguese.- Learning the Query Generation Patterns.- Exploiting Question Concepts for Query Expansion.- Experiment on Combining Sources of Evidence for Passage Retrieval.- Summarisation Through Discourse Structure.- LexTrim: A Lexical Cohesion Based Approach to Parse-and-Trim Style Headline Generation.- Generating Headline Summary from a Document Set.- Extractive Summarization Based on Word Information and Sentence Position.- Automatic Extraction and Learning of Keyphrases from Scientific Articles.- Automatic Annotation of Corpora for Text Summarisation: A Comparative Study.- Techniques for Improving the Performance of Naive Bayes for Text Classification.- Efficient Modeling of Analogy.- A Supervised Clustering Method for Text Classification.- Unsupervised Text Classification Using Kohonen's Self Organizing Network.- Enhancement of DTP Feature Selection Method for Text Categorization.- FASiL Adaptive Email Categorization System.- ESPClust: An Effective Skew Prevention Method for Model-Based Document Clustering.- A Method of Rapid Prototyping of Evolving Ontologies.- Resolution of Data Sparseness in Named Entity Recognition Using Hierarchical Features and Feature Relaxation Principle.- Learning Named Entity Recognition in Portuguese from Spanish.- A Simple Rule-Based Approach to Organization Name Recognition in Chinese Text.- Disentangling from Babylonian Confusion - Unsupervised Language Identification.- On the Syllabic Similarities of Romance Languages.- Automatic Language Identification Using Multivariate Analysis.- Design and Development of a System for the Detection of Agreement Errors in Basque.- An Experiment in Detection and Correction of Malapropisms Through the Web.- A Paragraph Boundary Detection System.