The researchpapersin this volumecomprisethe proceedingsofIceTAL 2010,an international conference on natural language processing (NLP). IceTAL was the seventh in the series of the TAL conferences, following GoTAL 2008 (Goth- burg, Sweden), FinTAL 2006 (Turku, Finland), EsTAL 2004 (Alicante, Spain), PorTAL2002(Faro,Portugal),VexTAL1999(Venice, Italy),andFracTAL1997 (Besançon,France).ThemaingoaloftheTALconferenceserieshasbeentobring together scientists representing linguistics, computer science, and related ?elds, sharing a common interest in the advancement of computational linguistics and NLP. IceTAL 2010, organized by the Icelandic Centre for Language Technology (ICLT) in Reykjavík, Iceland, successfully contributed to these goals. Our Program Committee (PC) consisted of 45 recognized researchers and professionals in the ?eld of NLP from Belgium, China, Cuba, Denmark, F- land, France, Germany, Iceland, Italy, Japan, Norway, Portugal, Spain, Sweden, Switzerland, United Kingdom, and the United States. We called for submissions both from academia and the industry on any topic that is of interest to the NLP community, particularly encouraging research - phasizingmultidisciplinaryaspectsofNLPandtheinterplaybetweenlinguistics, computer science, and application domains such as biomedicine, communication systems, public services, and educational technology.

Up-to-date results Fast track conference proceedings State-of-the-art report

Klappentext

This book constitutes the proceedings of the 7th International Conference on Advances in Natural Language Processing held in Reykjavik, Iceland, in August 2010.

Inhalt
Invited Talks.- Reliving the History: The Beginnings of Statistical Machine Translation and Languages with Rich Morphology.- Harmonizing WordNet and FrameNet.- Research Papers.- A Morphosyntactic Brill Tagger for Inflectional Languages.- Hybrid Syntactic-Semantic Reranking for Parsing Results of ECAs Interactions Using CRFs.- Automatic Distractor Generation for Domain Specific Texts.- Summarization as Feature Selection for Document Categorization on Small Datasets.- A Formal Ontology for a Computational Approach of Time and Aspect.- A Non-linear Semantic Mapping Technique for Cross-Language Sentence Matching.- Comparison of Paraphrase Acquisition Techniques on Sentential Paraphrases.- Digital Learning for Summarizing Arabic Documents.- Concept Based Representations for Ranking in Geographic Information Retrieval.- Using Machine Translation Systems to Expand a Corpus in Textual Entailment.- Frames in Formal Semantics.- Clustering E-Mails for the Swedish Social Insurance Agency What Part of the E-Mail Thread Gives the Best Quality?.- OpenMaTrEx: A Free/Open-Source Marker-Driven Example-Based Machine Translation System.- Head Finders Inspection: An Unsupervised Optimization Approach.- Estimating the Birth and Death Years of Authors of Undated Documents Using Undated Citations.- Using Temporal Cues for Segmenting Texts into Events.- Enriching the Adjective Domain in the Japanese WordNet.- Comparing SMT Methods for Automatic Generation of Pronunciation Variants.- Automatic Learning of Discourse Relations in Swedish Using Cue Phrases.- The Representation of Diatheses in the Valency Lexicon of Czech Verbs.- Symbolic Classification Methods for Patient Discharge Summaries Encoding into ICD.- User-Tailored Document Planning A Game-Theoretic Approach.- Anaphora Resolutionwith Real Preprocessing.- Automatic Construction of a Morphological Dictionary of Multi-Word Units.- Collocation Extraction in Turkish Texts Using Statistical Methods.- Towards the Design and Evaluation of ROILA: A Speech Recognition Friendly Artificial Language.- Time Expressions Ontology for Information Seeking Dialogues in the Public Transport Domain.- Reliability of the Manual Segmentation of Pauses in Natural Speech.- Large-Scale Language Modeling with Random Forests for Mandarin Chinese Speech-to-Text.- Design and Evaluation of an Agreement Error Detection System: Testing the Effect of Ambiguity, Parser and Corpus Type.- TectoMT: Modular NLP Framework.- Using Information from the Target Language to Improve Crosslingual Text Classification.- Event Detection Using Lexical Chain.- Using Comparable Corpora to Improve the Effectiveness of Cross-Language Information Retrieval.- Semi-automatic Endogenous Enrichment of Collaboratively Constructed Lexical Resources: Piggybacking onto Wiktionary.- Portable Extraction of Partially Structured Facts from the Web.- Passage Retrieval in Log Files: An Approach Based on Query Enrichment.- Part-of-Speech Tagging Using Parallel Weighted Finite-State Transducers.- Automated Email Answering by Text Pattern Matching.- A System to Control Language for Oral Communication.- Robust Semi-supervised and Ensemble-Based Methods in Word Sense Disambiguation.- The Effect of Semi-supervised Learning on Parsing Long Distance Dependencies in German and Swedish.- Shooting at Flies in the Dark: Rule-Based Lexical Selection for a Minority Language Pair.