Computational Linguistics and Intelligent Text Processing: 11th International Conference, CICLing 2010, Iasi, Romania, March 21-27, 2010, Proceedings (Lecture Notes in Computer Science, 6008)

th CICLing 2010 was the 11 Annual Conference on Intelligent Text Processing and Computational Linguistics. The CICLing conferences provide a wide-scope forum for discussion of the art and craft of natural language processing research as well as the best practices in its applications. This volume contains three invited papers and the regular papers accepted for oral presentation at the conference. The papers accepted for poster pres- tation were published in a special issue of another journal (see information on thewebsite).Since 2001,theproceedingsofCICLingconferenceshavebeen p- lished in Springer’s Lecture Notes in Computer Science series, as volumes 2004, 2276, 2588, 2945, 3406, 3878, 4394, 4919, and 5449. The volume is structured into 12 sections: – Lexical Resources – Syntax and Parsing – Word Sense Disambiguation and Named Entity Recognition – Semantics and Dialog – Humor and Emotions – Machine Translation and Multilingualism – Information Extraction – Information Retrieval – Text Categorization and Classi?cation – Plagiarism Detection – Text Summarization – Speech Generation The 2010 event received a record high number of submissions in the - year history of the CICLing series. A total of 271 papers by 565 authors from 47 countriesweresubmittedforevaluationbytheInternationalProgramCommittee (see Tables 1 and 2). This volume contains revised versions of 61 papers, by 152 authors, selected for oral presentation; the acceptance rate was 23%. Title Page Preface Organization Table of Contents Lexical Resources Invited Paper Planning the Future of Language Resources: The Role of the FLaReNet Network Why are Strategic Initiatives Necessary? An Inventory of Possible Strategic Actions for Language Resources and Technology Create and Mobilise a Unified and Committed Community of Language Resources and Technologies players Define Priorities, Formulate Strategies and Recommendations Analyse and Survey the LR&T Sector at Large Provide an Assessment of the Current Status of the Field Recommendations for Actions in the HLT Field Resource Production and Use Interoperability Issues Licensing, Maintenance and Preservation Evaluation and Validation Directions for Research and Development References Best Paper Award – Second Place Cross-Lingual Alignment of FrameNet Annotations through Hidden Markov Models Introduction An Hidden Markov Model of the Semantic Transfer States, Emissions and Transitions for Semantic Transfer Evaluation Conclusions References On the Automatic Generation of Intermediate Logic Forms for WordNet Glosses Introduction Previous Related Work Extended WordNet ISI/Boeing WN30lfs ILF Representation Discourse Entities Relations between Discourse Entities ILFs for WordNet 3.0 Glosses Processing Pipeline Description of ILF-WN Comparison with Other Approaches Conclusion and Future Work References Worth Its Weight in Gold or Yet Another Resource — A Comparative Study of Wiktionary, OpenThesaurus and GermaNet Introduction Description of Lexical Semantic Resources Related Work Representing Lexical Semantic Resources as Graphs Topological Analysis of Resources Content Analysis of Resources Conclusions and Future Work References Issues in Analyzing Telugu Sentences towards Building a Telugu Treebank Introduction Overview of Annotation Scheme Dependency Relations Issues Genitives Conjuncts Copula “ani" Constructions Parsing Issues Genitives Conjuncts Copula Conclusion and Future Work References EusPropBank: Integrating Semantic Information in the Basque Dependency Treebank Introduction The Resources Used PropBank/VerbNet The BDT Corpus The EADB Resource (Data Base for Basque Verbs) Mapping between Basque and English Verbs Based on Levin’s Classification The Annotation Process Representation of the Semantic Information (Definition of the Tag) AbarHitz, the Tool for Tagging Adapting AbarHitz to the Tagging of Semantic Roles Theoretical Problems and Decisions Conclusions References Morphological Annotation of a Corpus with a Collaborative Multiplayer Game Introduction Related Work TheGame Single Player Game Two Player Game Results Conclusion and Future Work References Syntax and Parsing Invited Paper Computational Models of Language Acquisition Introduction The Language Learning Task Evaluation Existing Approaches Cognitively-Motivated Computational Approaches to Child Language Acquisition Computational Grammar Induction Consolidating the Two Approaches Directions for Future Research References ETL Ensembles for Chunking, NER and SRL Introduction Entropy Guided Transformation Learning Template Sampling Redundant Transformation Rules ETL Committee ETL Committee Training Phase ETL Committee Classification Phase RelatedWork Experiments Machine Learning Modeling Text Chunking Named Entity Recognition Semantic Role Labeling ETL Committee Behavior Conclusions References Unsupervised Part-of-Speech Disambiguation for High Frequency Words and Its Influence on Unsupervised Parsing Introduction RelatedWork Motivation Clustering of Contexts Experiments Context Size andWeighting Function SingleWord Clusters Conclusion and Further Work References A Machine Learning Parser Using an Unlexicalized Distituent Model Introduction Related Work Classifier-Based Parsing Ensemble Learning in Classification Parser Architecture Experiments and Results Further Work Conclusion References Ontology-Based Semantic Interpretation as Grammar Rule Constraints Introduction Lexicalized Well-Founded Grammar Semantic Molecule Semantic Composition and Semantic Interpretation as Grammar Rule Constraints Ontology-Based Semantic Interpretation The Local Ontology-Based Semantic Interpreter Ambiguity Results Conclusions References Towards a Cascade of Morpho-syntactic Tools for Arabic Natural Language Processing NooJ: A Linguistic Development Platform Arabic Lexicon Formalization Verbs Nouns Pronouns Function Words Morphological Analysis and Automatic Tokenization Agglutinative Structure of Arabic Tokens Morphological Analysis and Grammatical Rules Definition Automatic Morpho-syntactic Analysis Automatic Vocalization Lexical Ambiguity Reduction Token’s Annotation Structure Spelling Checker and Corrector Automatic Arabic Named Entity Recognition Problems with Arabic Named Entity Recognition Automatic Named Entity Recognition Process Evaluation General Characteristics of the Evaluation Corpus Evaluation and Lexical Coverage Conclusion References An Open-Source Computational Grammar for Romanian Preliminaries Main Categories Nouns Adjectives Verbs Numerals Sentences Evaluation Future Work Related Projects Conclusions References Chinese Event Descriptive Clause Splitting with Structured SVMs Introduction Chinese Event Descriptive Clause Splitting Problem Structured SVMs Chinese Event Descriptive Clause Splitting with Structured SVMs Annotation Method Loss Function Emission Features Postprocessing with Rules Experiments Experimental Setting Experimental Results Conclusion References Word Sense Disambiguation and Named Entity Recognition Best Paper Award – First Place An Experimental Study on Unsupervised Graph-based Word Sense Disambiguation Introduction Related Work Supervised Word Sense Disambiguation Unsupervised Word Sense Disambiguation – The Graph-Based Methods Assigning Senses to Words in Semantic Graphs Semantic Graph Construction Spreading of Activation (SAN) Method PageRank (PR) Method HITS Method P-Rank Method WSD Methods Complexity Experimental Evaluation Empirical Evaluation of Unsupervised Graph-BasedWSD Methods Comparison with State of the Art WSD Methods Conclusions and Future Work References A Case Study of Using Web Search Statistics: Case Restoration Introduction Case Restoration Using Web Statistics in NLP Tasks Problem Formulation and Methodology System Architecture and Development Final Evaluation Other Findings Conclusion References A Named Entity Extraction Using Word Information Repeatedly Collected from Unlabled Data Introduction Japanese Named Entity Extraction Named Entity Extraction by Word-Unit Chunking Named Entity Extraction by Word-Unit Chunking Named Entity Extraction by Character-Unit Chunking Collecting NE-Related Labels of Words Repeatedly NE-Related Labels of Words Collecting NE-Related Labels of Words Experiments Machine Learning Algorithm Experimental Settings Experimental Results Related Work Comparison with Previous Work in Japanese NE Extraction Comparison with the other Semi-supervised Approaches Conclusion References A Distributional Semantics Approach to Simultaneous Recognition of Multiple Classes of Named Entities Introduction Background Distributional Semantics Semantic Vectors System GENIA Corpus Methods Results References Semantics and Dialog Invited Paper The Recognition and Interpretation of Motion in Language Introduction Semantic Annotation of Spatiotemporal Information Place Annotation with SpatialML and ISO-Space Annotation of Temporal Information with ISO-TimeML Towards a Spatiotemporal Markup Language Grounding the Annotation Modeling Motion in Language How Languages Talk about Movement Qualitative Models for Space and Time Dynamic Interval Temporal Logic Implementing Spatial Processing Algorithms Temporal Processing Place Finder Event Structure Lexicon Resource PathFinder Algorithm Corpus Annotation and Algorithm Evaluation References Flexible Disambiguation in DTS Introduction Dependency Tree Semantics (DTS) Positive and Negative Arcs Procedures for the Proper Management of $PN$ The Procedures $Convert$ and $Constrain$ Flexible Incremental Disambiguation in DTS Conclusion and Future Work References A Syntactic Textual Entailment System Based on Dependency Parser Introduction Related Works System Description Pre-processing Module Dependency Parser Module Matching Module Entailment Decision Experiments on the Development and the Test Data and the Results Conclusions References Semantic Annotation of Transcribed Audio Broadcast News Using Contextual Features in Graphical Discriminative Models Introduction NER with Graphical Models Conditional Random Fields Context-Based Approach for NER Hierarchical NEs Space Syntactic Annotation as an a Priori Information Efficient Features Induction Experiments Data and Evaluation Metrics NER Evaluation on Manually Transcribed Speech Model Adaptation for ASR Systems Conclusion References Lexical Chains Using Distributional Measures of Concept Distance Introduction Background Lexical Chains Text Segmentation Measures of Semantic Distance Method A General Algorithm for Lexical Chains Predicting Segment Boundaries Variants Evaluation Data Preparation Methodology Results Conclusion Summary of Results FutureWork References Incorporating Cohesive Devices into Entity Grid Model in Evaluating Local Coherence of Japanese Text Introduction Related Work Entity Grid Model Cohesive Devices to Be Incorporated Calculation of Transition Probabilities for Each Conjunction Type Reference Lexical Cohesion Refining Syntactic Roles Experiments Task 1: Discrimination of More Coherent Sentence Ordering Task 2: Summary Evaluation Conclusion References A Sequential Model for Discourse Segmentation Introduction Related Work Method Outline Conditional Random Fields Application to Discourse Segmentation Features Experiments Comparison to a Segmenter Based on Support Vector Machines Conclusion References Towards Automatic Detection and Tracking of Topic Change Introduction Motivation for Our Method Method Experiments Generating Overviews Conclusions and Further Work References Modelling Illocutionary Structure: Combining Empirical Studies with Formal Model Analysis Introduction Illocutionary Structures and Recursive Transition Networks Modelling Human-Human Dialogue Analysis Model Construction Formal Model Evaluation Formal Methodology and Tools Formal Specification of Dialogue Models Evaluation of the Doll’s House Dialogue Grammar Formal Comparison of Dialogue Models Discussion Conclusions References A Polyphonic Model and System for Inter-animation Analysis in Chat Conversations with Multiple Participants Introduction Polyphony and Inter-animation Automatic Analysis of Chats with Multiple Participants The NLP Pipe Pattern Language Content Analysis Words, Key Concepts, Voices, and Threads Polyphony, Inter-animation and Collaboration Conclusions References Humor and Emotions Computational Models for Incongruity Detection in Humour Introduction Data Models for Incongruity Detection Knowledge-Based Semantic Relatedness Corpus-Based Semantic Relatedness Domain Fitness Other Features Results Conclusions References Emotions in Words: Developing a Multilingual WordNet-Affect Introduction WordNet-Affect Development of Romanian and Russian WordNet Development of Romanian and Russian WordNet-Affect Automatic Translation Removing Irrelevant Translations Generating Romanian and Russian Synsets Inter-translator Agreement Conclusion and Future Work References Emotion Holder for Emotional Verbs – The Role of Subject and Syntax Introduction Related Work Subject Based Baseline Model Corpus Preparation Dependency Parsing and Subject Extraction Syntax Based Model Syntax Acquisition from VerbNet Argument Structure Acquisition Framework Evaluation Conclusion References Machine Translation and Multilingualism Best Paper Award – Third Place A Chunk-Driven Bootstrapping Approach to Extracting Translation Patterns Introduction Architecture Additional Linguistic Annotations Anchor Chunk Alignment Alignment of Complex Translational Correspondences Extraction Step Validation Step Experimental Results Bootstrapping Corpus Reference Corpus Evaluation Metrics Results Conclusion and Future Work References Computing Transfer Score in Example-Based Machine Translation Introduction EBMT System Architecture Word Substitution NE Recognition and Substitution Transfer Score Computation Mechanism General Idea Transfer Score Computation Algorithm Evaluation of the Transfer Score Metric Test Procedure Comparison with METEOR Comparison with BLEU Comparison with "Human Metric" Conclusions References Systematic Processing of Long Sentences in Rule Based Portuguese-Chinese Machine Translation Introduction Criteria in the Identification of Fragments in Long Sentences Specific Pattern Rules Punctuation and Conjunction Noun Phrase Chunks Long Sentence Partitioning and Translation Process Evaluation and Discussion Conclusion References Syntax Augmented Inversion Transduction Grammars for Machine Translation Introduction Stochastic Inversion Transduction Grammars with Phrasal Productions A SITG-Based Decoder for Machine Translation Inference of Syntax Augmented ITGs Linguistic Annotation of Non-terminals Experiments Data Results Conclusions References Syntactic Structure Transfer in a Tamil to Hindi MT System – A Hybrid Approach Introduction Our Approach Corpus Selection for Training Clause Identifier and Rule Learning Clause Identifier Rule Learning Using Transformation Based Learning (TBL) Semantic Classification of Postpositions and Case Markers Conclusion References A Maximum Entropy Approach to Syntactic Translation Rule Filtering Introduction Extraction of Translation Rules The Maximum Entropy Filter Maximum Entropy Models Rule Features Rule Features Alignment Data, Rule Sets, and Metrics Word Alignment Error Rate Consistent Translation Rule Score Experiments and Evaluation Filter Parameters MT Evaluation Discussion References Mining Parenthetical Translations for Polish-English Lexica Introduction Parenthetical Translation Conventions Corpora Pre-existing Corpora Dedicated Corpus Translation Extraction Preprocessing Filtering Out Acronyms Word Alignment Results Conclusions and Future Work References Automatic Generation of Bilingual Dictionaries Using Intermediary Languages and Comparable Corpora Introduction Related Work The Method Generation by Transitivity Validation with Comparable Corpora An Approach to Extract Translation Equivalents from Comparable Corpora A Case Study: The Elaboration of an English-Galician Dictionary The Existing Dictionaries and Generation by Transitivity Comparable Corpora and Validation The Final Not-noisy Lexicon Conclusions and Future Work References Hierarchical Finite-State Models for Speech Translation Using Categorization of Phrases Introduction Phrase-Based Speech Translation with Finite-State Transducers Learning a Phrase-Based Transducer Hierarchical Translation Model $P_{M_{CP_{L}}}$ Definition of the Model Inference of the Model Experiments Concluding Remarks and Future Work References Drive-by Language Identification A Byproduct of Applied Prototype Semantics Introduction Theoretical Considerations Implementation Related Work Evaluation Conclusions References Identification of Translationese: A Machine Learning Approach Introduction Related Work Methodology Evaluation Classification Results Experiments on Separate Test Datasets Results Analysis Conclusions and Further Research References Information Extraction Acquiring IE Patterns through Distributional Lexical Semantic Models Introduction Acquiring Patterns from Corpora Learning Information Extraction Patterns Modeling Individual Frame Elements Induction of Semantic Patterns Compiling Patterns in the Knowledge Base Empirical Evaluation Discussion References Multi-view Bootstrapping for Relation Extraction by Exploring Web Features and Linguistic Features Introduction Related Work Multi-view Bootstrapping Outline of the Proposed Method Feature Acquisition Feature Clustering Multi-view Bootstrapping with View Disagreement Detection Experiments Experimental Setup Feature Clusters Empirical Analysis Conclusions References Sequential Patterns to Discover and Characterise Biological Relations Introduction Sequential Patterns for Information Extraction Sequential Patterns Extraction of Sequential Patterns in Texts Constraints and Recursive Mining Selection and Categorisation of Patterns Experiments Extraction Rules Application: Detection and Characterisation of Gene Interactions Discussion Conclusion References Extraction of Genic Interactions with the Recursive Logical Theory of an Ontology Introduction Related Works Information Extraction Platform Ontology Population Module Query Module Learning the Logical Theory of the Ontology Results Conclusion and Perspectives References Ontological Parsing of Encyclopedia Information Introduction Problem Statement and Basic Algorithm Lexicographic Processing Morphology and Syntax Relation Recognition Import to Ontology Wikipedia Parsing Conclusion References Information Retrieval Selecting the N-Top Retrieval Result Lists for an Effective Data Fusion Introduction Related Work Selecting the N-Top Result Lists Experimental Setup Data Sets and Result Lists Data Fusion Methods Evaluation Measure Experimental Results Baseline Results Results of the Proposed Approach Conclusions and Future Work References Multi Word Term Queries for Focused Information Retrieval Introduction Combining Automatic and Interactive Query Expansion Language Model Query Expansion Enterprise Search Document Collection and Tasks Results Based on Usual Average Precision Results Based on Inferred Average Precision FocusedRetrieval INEX 2008 Ad-Hoc Track Results Conclusions References Optimal IR: How Far Away? Introduction Method Dataset Measure Passage2 and Optimization Measure Aspect and Optimization Perfect Runs Experimental Results Discussion and Analysis Conclusion References Adaptive Term Weighting through Stochastic Optimization Introduction Term Weighting as Linear Transformation On-Line Learning for Term Weighting Experiments Data Sets Learning a GivenWeighing Scheme Weight Adaption for k-NN Classification Conclusion References Text Categorization and Classification Enhancing Text Classification by Information Embedded in the Test Set Introduction Prototype-Based Classification The Proposed Method Experimental Evaluation Datasets Evalaution Measure Baseline Results Results Conclusions References Rank Distance Aggregation as a Fixed Classifier Combining Rule for Text Categorization Introduction Motivation Background New to Our Approach Fixed and Trained Combiners Rank Distance Aggregation Rankings Rank Distance Rank Aggregation Rank Distance Categorization Properties of RDC Experiments in Text Categorization Summary and Conclusions References The Influence of Collocation Segmentation and Top 10 Items to Keyword Assignment Performance Introduction Conceptual Thesaurus Collocation Segmentation DataSets Producing Feature Vectors and Assigning Descriptors to a Text Results Conclusion References A General Bio-inspired Method to Improve the Short-Text Clustering Task Introduction The PAntSA Algorithm Using Silhouette Coefficient Information of Previous Clusterings Using an Attraction-Based Comparison PAntSA, a Partitional Simplified Version of AntSA Experimental Setting and Analysis of Results Experimental Results Conclusions and Future Work References An Empirical Study on the Feature’s Type Effect on the Automatic Classification of Arabic Documents Introduction Automatic Document Classification The Difficulties Encountered with Arabic Unvowelled Writing The Complex Structure of the Arabic Word-Form Support Vector Machines (SVM) Na\"{i}ve Bayesian Networks The Dataset Feature Selection Metrics Evaluation Metrics Experimental Results Conclusion References Plagiarism Detection Word Length n-Grams for Text Re-use Detection Introduction Corpora PAN-PC-09 Corpus Co-derivatives Corpus Method Definition Notation Length Encoding Similarity Estimation Experiments Experiments on the PAN-PC-09 Corpus Experiments on the Co-derivatives Corpus Experiments on Process Speed Conclusions References Who’s the Thief? Automatic Detection of the Direction of Plagiarism Introduction Related Work Methods Dataset Finding the Asymmetry Measuring and Using the Asymmetry Results and Analysis Discussion and Conclusion References Text Summarization Best Student Paper Award Integer Linear Programming for Dutch Sentence Compression Introduction Background Language Tools Parsing Latent Words Language Model Integer Linear Programming Approach to Sentence Compression Integer Linear Programming Integer Programming for Sentence Compression Linguistic Constraints Significance Model Evaluation Data Systems Evaluation Results Human Evaluation Automatic Evaluation Discussion Conclusion References GEMS: Generative Modeling for Evaluation of Summaries Introduction Current Summarization Evaluations Content Evaluations Automated Content Evaluations Approach Generative Modeling of Reference Summaries Signature Terms Experiments and Evaluations Baselines Datasets Evaluations Results Discussion Conclusion References Quantitative Evaluation of Grammaticality of Summaries Introduction Grammaticality in Summaries Ngram Model Longest Common Subsequence (LCS) Class Model Evaluation Conclusion and Discussion References Speech Generation Integrating Contrast in a Framework for Predicting Prosody Introduction Theoretical Background Experimental Setup Experiment A - Topics Experiment B - Foci Results Discussion Integration to an Annotation Framework Conclusion References Author Index This book constitutes the proceedings of the 11th International Conference on Computational Linguistics and Intelligent Text Processing, held in Ia??i, Romania, in March 2010. The 60 paper included in the volume were carefully reviewed and selected from numerous submissions. The book also includes 3 invited papers. The topics covered are: lexical resources, syntax and parsing, word sense disambiguation and named entity recognition, semantics and dialog, humor and emotions, machine translation and multilingualism, information extraction, information retrieval, text categorization and classification, plagiarism detection, text summarization, and speech generation Includes the proceedings of the 11th International Conference on Computational Linguistics and Intelligent Text Processing, held in IaAui, Romania, in March 2010. This title covers topics such as: lexical resources, syntax and parsing, word sense disambiguation and named entity recognition, semantics and dialog, and humor and emotions.