This book constitutes the refereed proceedings of the 5th International Conference on Natural Language Processing, FinTAL 2006, held in Turku, Finland in August 2006. The book presents 72 revised full papers together with 1 invited talk and the extended abstracts of 2 invited keynote addresses. The papers address all current issues in computational linguistics and monolingual and multilingual intelligent language processing - theory, methods and applications.
Keynote Addresses.- Recursion in Natural Languages.- The Explanatory Combinatorial Dictionary as the Key Tool in Machine Translation.- A Finite-State Approximation of Optimality Theory: The Case of Finnish Prosody.- Research Papers.- A Bilingual Corpus of Novels Aligned at Paragraph Level.- A Computational Implementation of Internally Headed Relative Clause Constructions.- A Corpus-Based Empirical Account of Adverbial Clauses Across Speech and Writing in Contemporary British English.- A Korean Syntactic Parser Customized for Korean-English Patent MT System.- A Scalable and Distributed NLP Architecture for Web Document Annotation.- A Straightforward Method for Automatic Identification of Marginalized Languages.- A Text Mining Approach for Definition Question Answering.- Accommodating Multiword Expressions in an Arabic LFG Grammar.- Analysis of EU Languages Through Text Compression.- Applying Latent Dirichlet Allocation to Automatic Essay Grading.- Automatic Acquisition of Semantic Relationships from Morphological Relatedness.- Automatic Feature Extraction for Question Classification Based on Dissimilarity of Probability Distributions.- Cat3LB and Cast3LB: From Constituents to Dependencies.- Classification of News Web Documents Based on Structural Features.- Cognition and Physio-acoustic Correlates — Audio and Audio-visual Effects of a Short English Emotional Statement: On JL2, FL2 and EL1.- Compiling Generalized Two-Level Rules and Grammars.- Computer Analysis of the Turkmen Language Morphology.- Coordination Structures in a Typed Feature Structure Grammar: Formalization and Implementation.- Cue-Based Interpretation of Customer’s Requests: Analysis of Estonian Dialogue Corpus.- Czech-English Phrase-Based Machine Translation.- Deep vs. Shallow Semantic Analysis Applied to Textual Entailment Recognition.- Dictionary-Free Morphological Classifier of Russian Nouns.- Discourse Segmentation of German Written Texts.- Document Clustering Based on Maximal Frequent Sequences.- Enriching Thesauri with Hierarchical Relationships by Pattern Matching in Dictionaries.- Evaluation of Alignment Methods for HTML Parallel Text.- Experiments in Passage Selection and Answer Identification for Question Answering.- Extracting Idiomatic Hungarian Verb Frames.- Extracting Term Collocations for Directing Users to Informative Web Pages.- Feasibility of Enriching a Chinese Synonym Dictionary with a Synchronous Chinese Corpus.- Finding Spanish Syllabification Rules with Decision Trees.- Identifying Text Discourse Structure of the Narratives Describing Psychiatric Patients’ Defense Mechanisms.- Implementing a Rule-Based Speech Synthesizer on a Mobile Platform.- Improving Phrase-Based Statistical Translation Through Combination of Word Alignments.- Improving Statistical Word Alignments with Morpho-syntactic Transformations.- Improving Term Extraction with Terminological Resources.- Improving Thai Spelling Recognition with Tone Features.- Incorporating External Information in Bayesian Classifiers Via Linear Feature Transformations.- Is a Morphologically Complex Language Really that Complex in Full-Text Retrieval?.- Language Independent Answer Prediction from the Web.- Language Model Mixtures for Contextual Ad Placement in Personal Blogs.- Local Constraints on Arabic Word Order.- MEDITE: A Unilingual Textual Aligner.- Maximum Likelihood Alignment of Translation Equivalents.- Measuring Intelligibility of Japanese Learner English.- Morphological Lexicon Extraction from Raw Text Data.- On the Use of Topic Models for Word Completion.- Ord i Dag: Mining Norwegian Daily Newswire.- Paraphrase Identification on the Basis of Supervised Machine Learning Techniques.- Passage Filtering for Open-Domain Question Answering.- Persian in MULTEXT-East Framework.- Prerequisites for a Comprehensive Dictionary of Serbian Compounds.- Regular Approximation of Link Grammar.- Segmental Duration in Utterance-Initial Environment: Evidence from Finnish Speech Corpora.- Selection Strategies for Multi-label Text Categorization.- Some Problems of Prepositional Phrases in Machine Translation.- Speech Confusion Index (Ø): A Recognition Rate Indicator for Dysarthric Speakers.- Statistical Machine Translation of German Compound Words.- Summarizing Documents in Context: Modeling the User’s Information Need.- Supervised TextRank.- Tagging a Morphologically Complex Language Using Heuristics.- Terminology Structuring Through the Derivational Morphology.- Text Segmentation Criteria for Statistical Machine Translation.- The Classificatim Sense-Mining System.- The Role of Verb Sense Disambiguation in Semantic Role Labeling.- The Vowel Game: Continuous Real-Time Visualization for Pronunciation Learning with Vowel Charts.- Towards a Framework for Evaluating Syntactic Parsers.- Towards the Improvement of Statistical Translation Models Using Linguistic Features.- Treating Unknown Light Verb Construction in Korean-to-English Patent MT.- Trees as Contexts in Formal Language Generation.- Two String-Based Finite-State Models of the Semantics of Calendar Expressions.- Using Alignment Templates to Infer Shallow-Transfer Machine Translation Rules.
