Recent advances in natural language processing IV : selected papers from RANLP 2005 / / edited by Nicolas Nicolov ... [et al.]

• Record Nr.: UNINA9910815513403321
• Pubbl/distr/stampa: Amsterdam ; ; Philadelphia, : John Benjamins Pub., c2007
• ISBN: 1-282-15196-7; 9786612151965; 90-272-9128-4
• Edizione: [1st ed.]
• Descrizione fisica: xii, 307 p. : ill., map
• Collana: Amsterdam studies in the theory and history of linguistic science. Series IV, Current issues in linguistic theory, , 0304-0763 ; ; v. 292
• Altri autori (Persone): NicolovNicolas
• Disciplina: 410.285
• Soggetti: Computational linguistics
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Bibliographic Level Mode of Issuance: Monograph
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Recent Advances in Natural Language Processing IV -- Editorial page -- Title page -- LCC data -- CONTENTS -- Editors' Foreword -- Linguistic Challenges for Computationalists -- 1 Introduction -- 2 Computational linguistics -- 3 Dialectology -- 4 Diachronic linguistics -- 5 Language acquisition -- 6 Language contact -- 7 Other areas -- 8 Conclusions -- REFERENCES -- NLP: An Information Extraction Perspective -- 1 The challenges of information extraction -- 2 Identifying instances of a linguistic expression -- 3 Finding linguistic expressions of an event or relation -- 4 Discovering what's important -- REFERENCES -- Semantic Indexing using Minimum Redundancy Cut in Ontologies -- 1 Introduction -- 2 Minimum redundancy cut in an ontology -- 3 Experiments -- 4 Discussion and conclusion -- REFERENCES -- Indexing and Querying Linguistic Metadata and Document Content -- 1 Introduction -- 2 GATE -- 3 ANNIC -- 4 ANNIC user interface -- 5 Applications of ANNIC -- 6 Performance results -- 7 Related work -- REFERENCES -- Term Representation with Generalized Latent Semantic Analysis -- 1 Introduction -- 2 Generalized Latent Semantic Analysis -- 3 Related approaches -- 4 Experiments -- 5 Conclusion and future work -- REFERENCES -- Multilingual Dependency Parsing: A Pipeline Approach -- 1 Introduction -- 2 Dependency parsing as a pipeline model -- 3 Experimental study -- 4 Extensions: Non-projective trees ; and edge labels -- 5 Conclusions and further work -- REFERENCES -- How Does Treebank Annotation Influence Parsing? -- 1 Introduction -- 2 The Negra and the T¨uBa-D/Z treebanks -- 3 Comparing treebanks for parsing -- 4 Discussion of the results of the comparison -- 5 Conclusion and future work -- REFERENCES -- The SenSem Project: Syntactico-Semantic Annotation of Sentences in Spanish -- 1 Introduction -- 2 Related work -- 3 Levels of annotation.; 4 Annotation process -- 5 Preliminary results of annotation -- 6 Conclusions and future work -- REFERENCES -- Generating Referring Expressions: Past, Present and Future -- 1 Introduction -- 2 What's involved in referring expression generation -- 3 A history of work in the area -- 4 Outstanding issues -- 5 Conclusions -- REFERENCES -- A Data-driven Approach to Pronominal Anaphora Resolution for German -- 1 Introduction -- 3 Data -- 4 Experiments -- 5 Evaluation -- 6 Comparison with related work -- 7 Summary and future work -- REFERENCES -- Efficient Spam Analysis for Weblogs through URL Segmentation -- 1 Introduction -- 2 Engineering of splogs -- 3 URL segmentation -- 4 URL classification -- 5 Experiments and results -- 6 Discussion -- 7 Future work -- 8 Conclusions -- REFERENCES -- Document Classification Using Semantic Networks with an Adaptive Similarity Measure -- 1 Introduction -- 2 Document representation -- 3 Weight update algorithm -- 4 Evaluation -- 5 Conclusions and future work -- REFERENCES -- Appendix 1 -- Text Summarization for Improved Text Classification -- 1 Introduction -- 2 Text categorization using extractive summarization -- 3 Experimental results -- 4 Related work -- 5 Conclusions -- REFERENCES -- Exploiting Linguistic Cues to Classify Rhetorical Relations -- 1 Introduction -- 2 Related research -- 3 Our approach -- 4 Experiments -- 5 Conclusion -- REFERENCES -- Tree Edit Distance for Textual Entailment -- 1 Introduction -- 2 Tree edit distance on dependency trees -- 3 System architecture -- 4 Experiments and results -- 5 Discussion -- 6 Conclusion and future work -- REFERENCES -- A Genetic Algorithm for Optimising Information Retrieval with Linguistic Features in Question Answering -- 1 Introduction -- 2 Information retrieval with linguistic features -- 3 A Genetic Algorithm for query optimisation -- 4 Experiments.; 5 Conclusions and future work -- REFERENCES -- Lexico-Syntactic Subsumption for Textual Entailment -- 1 Introduction -- 2 Related work -- 3 Approach -- 4 Experiments and results -- 5 Conclusions -- REFERENCES -- A Knowledge-based Approach to Text-to-Text Similarity -- 1 Introduction -- 2 Measuring text semantic similarity -- 3 Application 1: Paraphrase and entailment recognition -- 4 Application 2: Word sense similarity -- 5 Discussion and conclusions -- REFERENCES -- A Simple WWW-based Method for Semantic Word Class Acquisition -- 1 Introduction -- 2 Previous work -- 3 Proposed method -- 4 Experiments -- 5 Conclusions -- REFERENCES -- Automatic Building of Wordnets -- 1 Introduction -- 2 Assumptions -- 3 Selection of concepts and resources used -- 4 Notation introduction and the idea of heuristics -- 5 The synonymy heuristic rule -- 6 The hyperonymy heuristic rule -- 7 The domain heuristic -- 8 The monolingual dictionary heuristic rule -- 9 Combining results -- 10 Import of relations -- 11 Conclusions -- REFERENCES -- Lexical Transfer Selection Using Annotated Parallel Corpora -- 1 Background -- 2 Proposed method -- 3 Results -- REFERENCES -- Multi-Perspective Evaluation of the FAME Speech-to-Speech Translation System for Catalan, English and Spanish -- 1 Introduction -- 2 System architecture -- 3 Evaluation -- 4 Conclusions -- REFERENCES -- Parallel Corpora for Medium Density Languages -- 1 Introduction -- 2 Collecting and preparing the corpus -- 3 Sentence level alignment -- 4 ; Evaluation -- 5 Conclusion -- REFERENCES -- The Role of Data in NLP: The Case for Dataset Profiling -- 1 Data matters -- 2 Sparseness -- 3 Profiling collection bias -- 4 Measures for profiling -- 5 Conclusion -- REFERENCES -- Even Very Frequent Function Words Do Not Distribute Homogeneously -- 1 Introduction -- 2 Experimental framework -- 3 Experimental results.; 4 Conclusion -- REFERENCES -- Exploiting Parallel Texts to Produce a Multilingual Sense Tagged Corpus for Word Sense Disambiguation -- 1 Introduction -- 2 The sense tagging approach -- 3 Evaluation and discussion -- 4 Conclusions -- REFERENCES -- Detecting Dangerous Coordination Ambiguities Using Word Distribution -- 1 Introduction -- 2 Methodology -- 3 Related research -- 4 Disambiguation empirical study -- 5 Evaluation and discussion -- 6 Conclusions and further work -- REFERENCES -- List and Addresses of Contributors -- Index of Subjects and Terms -- The series Current Issues in Linguistic Theory (CILT).
• Sommario/riassunto: This volume brings together selected and revised papers from the international conference on "Recent Advances in Natural Language Processing", held in Borovets, Bulgaria, in September 2005. The best papers have been selected for this volume with the aim to reflect the most promising and significant trends in natural language processing. The volume covers a wide variety of topics in Natural Language Processing, including information extraction, indexing, latent semantic analysis, dependency parsing, anaphora and referring expressions, spam analysis, document classification, rhetorical relations, textual entailment, question answering, ontologies, word sense disambiguation, machine translation, treebanks and corpora.