Computational Linguistics and Intelligent Text Processing: 6th International Conference, CICLing 2005, Mexico City, Mexico, February 13-19, 2005, Proceedings (Lecture Notes in Computer Science (3406))

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. Front Matter....Pages - An Overview of Probabilistic Tree Transducers for Natural Language Processing....Pages 1-24 A Modular Account of Information Structure in Extensible Dependency Grammar....Pages 25-36 Modelling Grammatical and Lexical Knowledge: A Declarative Approach....Pages 37-47 Constructing a Parser for Latin....Pages 48-59 Parsing Korean Case Phenomena in a Type-Feature Structure Grammar....Pages 60-72 A Computational Model of the Spanish Clitic System....Pages 73-82 A Parallel Approach to Syllabification....Pages 83-87 Towards Developing Probabilistic Generative Models for Reasoning with Natural Language Representations....Pages 88-99 Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing....Pages 100-111 Assigning Function Tags with a Simple Model....Pages 112-115 Finding Discourse Relations in Student Essays....Pages 116-119 Regional Versus Global Finite-State Error Repair....Pages 120-131 Lexicalized Beam Thresholding Parsing with Prior and Boundary Estimates....Pages 132-141 Unsupervised Evaluation of Parser Robustness....Pages 142-154 Mutual Information Independence Model Using Kernel Density Estimation for Segmenting and Labeling Sequential Data....Pages 155-166 Applying Conditional Random Fields to Chinese Shallow Parsing....Pages 167-176 Distributional Thesaurus Versus WordNet: A Comparison of Backoff Techniques for Unsupervised PP Attachment....Pages 177-188 Automatic Recognition of Czech Derivational Prefixes....Pages 189-197 Korma 2003: Newly Improved Korean Morpheme Analysis Module for Reducing Terminological and Spacing Errors in Document Analysis....Pages 198-201 Word Extraction Based on Semantic Constraints in Chinese Word-Formation....Pages 202-213 Evaluating Evaluation Methods for Generation in the Presence of Variation....Pages 341-351 Reconciling Parameterization, Configurability and Optimality in Natural Language Generation via Multiparadigm Programming....Pages 352-356 Using Directed Graph Based BDMM Algorithm for Chinese Word Segmentation....Pages 214-217 Message Automata for Messages with Variants, and Methods for Their Translation....Pages 357-376 Entity-Based Noun Phrase Coreference Resolution....Pages 218-221 The Right Frontier Constraint as Conditional....Pages 222-225 Name Discrimination by Clustering Similar Contexts....Pages 226-237 Word Sense Disambiguation by Semi-supervised Learning....Pages 238-241 Crossing Parallel Corpora and Multilingual Lexical Databases for WSD....Pages 242-245 A Mapping Between Classifiers and Training Conditions for WSD....Pages 246-249 Multiwords and Word Sense Disambiguation....Pages 250-262 Context Expansion with Global Keywords for a Conceptual Density-Based WSD....Pages 263-266 Two Web-Based Approaches for Noun Sense Disambiguation....Pages 267-279 Finding Instance Names and Alternative Glosses on the Web: WordNet Reloaded....Pages 280-292 Automatic Synonym Acquisition Based on Matching of Definition Sentences in Multiple Dictionaries....Pages 293-304 Enriching WordNet with Derivational Subnets....Pages 305-311 Customisable Semantic Analysis of Texts....Pages 312-323 ITOLDU, a Web Service to Pool Technical Lexical Terms in a Learning Environment and Contribute to Multilingual Lexical Databases....Pages 324-332 Building a Situation-Based Language Knowledge Base....Pages 333-336 Unsupervised Learning of P NP P Word Combinations....Pages 337-340 The UNL Initiative: An Overview....Pages 377-387 Interactive Resolution of Intrinsic and Translational Ambiguity in a Machine Translation System....Pages 388-399 Chinese-Japanese Clause Alignment....Pages 400-412 Direct Combination of Spelling and Pronunciation Information for Robust Back-Transliteration....Pages 413-424 A Prosodic Diphone Database for Korean Text-to-Speech Synthesis System....Pages 425-428 On a Pitch Detection Method Using Noise Reduction....Pages 429-432 Toward Acoustic Models for Languages with Limited Linguistic Resources....Pages 433-436 A Study on Pitch Detection in Time-Frequency Hybrid Domain....Pages 437-440 VoiceUNL: A Semantic Representation of Emotions Within Universal Networking Language Formalism Based on a Dialogue Corpus Analysis....Pages 441-451 Combining Multiple Statistical Classifiers to Improve the Accuracy of Task Classification....Pages 452-462 A Finite State Network for Phonetic Text Processing....Pages 463-473 Language Documentation: The Nahuatl Grammar....Pages 474-485 Creating Subjective and Objective Sentence Classifiers from Unannotated Texts....Pages 486-497 Instance Pruning by Filtering Uninformative Words: An Information Extraction Case Study....Pages 498-509 Incremental Information Extraction Using Tree-Based Context Representations....Pages 510-521 Learning Information Extraction Rules for Protein Annotation from Unannotated Corpora....Pages 522-534 Transformation-Based Information Extraction Using Learned Meta-rules....Pages 535-538 A Machine Learning Approach to Information Extraction....Pages 539-547 Automatic Time Expression Labeling for English and Chinese Text....Pages 548-559 Integrating Natural Language Techniques in OO-Method....Pages 560-571 Document Re-ordering Based on Key Terms in Top Retrieved Documents....Pages 572-583 Merging Case Relations into VSM to Improve Information Retrieval Precision....Pages 584-592 Evaluating Document-to-Document Relevance Based on Document Language Model: Modeling, Implementation and Performance Evaluation....Pages 593-603 Retrieval Efficiency of Normalized Query Expansion....Pages 604-607 Selecting Interesting Articles Using Their Similarity Based Only on Positive Examples....Pages 608-611 Question Classification in Spanish and Portuguese....Pages 612-619 Learning the Query Generation Patterns....Pages 620-623 Exploiting Question Concepts for Query Expansion....Pages 624-627 Experiment on Combining Sources of Evidence for Passage Retrieval....Pages 628-631 Summarisation Through Discourse Structure....Pages 632-644 LexTrim: A Lexical Cohesion Based Approach to Parse-and-Trim Style Headline Generation....Pages 645-648 Generating Headline Summary from a Document Set....Pages 649-652 Extractive Summarization Based on Word Information and Sentence Position....Pages 653-656 Automatic Extraction and Learning of Keyphrases from Scientific Articles....Pages 657-669 Automatic Annotation of Corpora for Text Summarisation: A Comparative Study....Pages 670-681 Techniques for Improving the Performance of Naive Bayes for Text Classification....Pages 682-693 Efficient Modeling of Analogy....Pages 694-703 A Supervised Clustering Method for Text Classification....Pages 704-714 Unsupervised Text Classification Using Kohonen’s Self Organizing Network....Pages 715-718 Enhancement of DTP Feature Selection Method for Text Categorization....Pages 719-722 FASiL Adaptive Email Categorization System....Pages 723-734 ESPClust: An Effective Skew Prevention Method for Model-Based Document Clustering....Pages 735-745 A Method of Rapid Prototyping of Evolving Ontologies ....Pages 746-749 Resolution of Data Sparseness in Named Entity Recognition Using Hierarchical Features and Feature Relaxation Principle....Pages 750-761 Learning Named Entity Recognition in Portuguese from Spanish....Pages 762-768 A Simple Rule-Based Approach to Organization Name Recognition in Chinese Text....Pages 769-772 Disentangling from Babylonian Confusion – Unsupervised Language Identification....Pages 773-784 On the Syllabic Similarities of Romance Languages....Pages 785-788 Automatic Language Identification Using Multivariate Analysis....Pages 789-792 Design and Development of a System for the Detection of Agreement Errors in Basque....Pages 793-802 An Experiment in Detection and Correction of Malapropisms Through the Web....Pages 803-815 A Paragraph Boundary Detection System....Pages 816-826 Back Matter....Pages -

This book constitutes the refereed proceedings of the 6th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2005, held in Mexico City, Mexico in February 2005.

The 53 revised full papers and 35 revised short papers presented together with 4 invited papers were carefully reviewed and selected from 151 submissions. The papers are organized in topical sections on computational linguistics forum; semantics and discourse; parsing and syntactic disambiguation; morphology; anaphora and conference; word sense disambiguation; lexical resources; natural language generation; machine translation; speech and natural language interfaces; language documentation; information extraction, information retrieval; question answering; summarization; text classification, categorization, and clustering; named entity recognition; language identification; and spelling and style checking.

This two-volume set, consisting of LNCS 7816 and LNCS 7817, constitutes the thoroughly refereed proceedings of the 13th International Conference on Computer Linguistics and Intelligent Processing, CICLING 2013, held on Samos, Greece, in March 2013. The total of 91 contributions presented was carefully reviewed and selected for inclusion in the proceedings. The papers are organized in topical sections named: general techniques; lexical resources; morphology and tokenization; syntax and named entity recognition; word sense disambiguation and coreference resolution; semantics and discourse; sentiment, polarity, subjectivity, and opinion; machine translation and multilingualism; text mining, information extraction, and information retrieval; text summarization; stylometry and text simplification; and applications.