Text, Speech and Dialogue: 15th International Conference, TSD 2012, Brno, Czech Republic, September 3-7, 2012, Proceedings (Lecture Notes in Computer Science, 7499)

This book constitutes the refereed proceedings of the 15th International Conference on Text, Speech and Dialogue, TSD 2012, held in Brno, Czech Republic, in September 2012. The 82 papers presented together with 2 invited talks were carefully reviewed and selected from 173 submissions. The papers are organized in topical sections on corpora and language resources, speech recognition, tagging, classification and parsing of text and speech, speech and spoken language generation, semantic processing of text and speech, integrating applications of text and speech processing, machine translation, automatic dialogue systems, multimodal techniques and modeling. Front Matter....Pages - Front Matter....Pages 1-1 Getting to Know Your Corpus....Pages 3-15 Coreference Resolution: To What Extent Does It Help NLP Applications?....Pages 16-27 Front Matter....Pages 29-29 Semantic Similarity Functions in Word Sense Disambiguation....Pages 31-38 Opinion Mining on a German Corpus of a Media Response Analysis....Pages 39-46 The Soundex Phonetic Algorithm Revisited for SMS Text Representation....Pages 47-55 Sentence Modality Assignment in the Prague Dependency Treebank....Pages 56-63 Literacy Demands and Information to Cancer Patients....Pages 64-71 Expanding Opinion Attribute Lexicons....Pages 72-80 Taggers Gonna Tag: An Argument against Evaluating Disambiguation Capacities of Morphosyntactic Taggers....Pages 81-87 An Ambiguity Aware Treebank Search Tool....Pages 88-94 A New Annotation Tool for Aligned Bilingual Corpora....Pages 95-104 Optimizing Sentence Boundary Detection for Croatian....Pages 105-111 Mining the Web for Idiomatic Expressions Using Metalinguistic Markers....Pages 112-118 Using Tree Transducers for Detecting Errors in a Treebank of Polish....Pages 119-126 Combining Manual and Automatic Annotation of a Learner Corpus....Pages 127-134 A Manually Annotated Corpus of Pharmaceutical Patents....Pages 135-142 Large-Scale Experiments with NP Chunking of Polish....Pages 143-149 Mapping a Lexical Semantic Resource to a Common Framework of Computational Lexicons....Pages 150-157 The Rule-Based Approach to Czech Grammaticalized Alternations....Pages 158-165 Semi-supervised Acquisition of Croatian Sentiment Lexicon....Pages 166-173 Front Matter....Pages 29-29 Towards a Constraint Grammar Based Morphological Tagger for Croatian....Pages 174-182 A Type-Theoretical Wide-Coverage Computational Grammar for Swedish....Pages 183-190 Application of Lemmatization and Summarization Methods in Topic Identification Module for Large Scale Language Modeling Data Filtering....Pages 191-198 Experiments and Results with Diacritics Restoration in Romanian....Pages 199-206 Supervised Distributional Semantic Relatedness....Pages 207-214 PSI-Toolkit....Pages 215-222 Heterogeneous Named Entity Similarity Function....Pages 223-231 Joint Part-of-Speech Tagging and Named Entity Recognition Using Factor Graphs....Pages 232-239 Assigning Deep Lexical Types....Pages 240-247 SBFC: An Efficient Feature Frequency-Based Approach to Tackle Cross-Lingual Word Sense Disambiguation....Pages 248-255 Dependency Relations Labeller for Czech....Pages 256-263 Preliminary Study on Automatic Induction of Rules for Recognition of Semantic Relations between Proper Names in Polish Texts....Pages 264-271 Actionable Clause Detection from Non-imperative Sentences in Howto Instructions: A Step for Actionable Information Extraction....Pages 272-281 Authorship Attribution: Comparison of Single-Layer and Double-Layer Machine Learning....Pages 282-289 Key Phrase Extraction of Lightly Filtered Broadcast News....Pages 290-297 Using a Double Clustering Approach to Build Extractive Multi-document Summaries....Pages 298-305 A Comparative Study of the Impact of Statistical and Semantic Features in the Framework of Extractive Text Summarization....Pages 306-313 Using Dependency-Based Annotations for Authorship Identification....Pages 314-319 A Space-Efficient Phrase Table Implementation Using Minimal Perfect Hash Functions....Pages 320-327 Common Sense Inference Using Verb Valency Frames....Pages 328-335 Front Matter....Pages 29-29 A Genetic Programming Experiment in Natural Language Grammar Engineering....Pages 336-344 User Modeling for Language Learning in Facebook....Pages 345-352 Detection of Semantic Compositionality Using Semantic Spaces....Pages 353-361 User Adaptation in a Hybrid MT System....Pages 362-369 Using Cognates to Improve Lexical Alignment Systems....Pages 370-377 Disambiguating Word Translations with Target Language Models....Pages 378-385 English-Vietnamese Machine Translation of Proper Names....Pages 386-393 Improved Phrase Translation Modeling Using MAP Adaptation....Pages 394-402 Front Matter....Pages 403-403 A Romanian Language Corpus for a Commercial Text-To-Speech Application....Pages 405-414 Making Community and ASR Join Forces in Web Environment....Pages 415-421 Unsupervised Synchronization of Hidden Subtitles with Audio Track Using Keyword Spotting Algorithm....Pages 422-430 Did You Say What I Think You Said?....Pages 431-437 Dealing with Numbers in Grapheme-Based Speech Recognition....Pages 438-445 Discretion of Speech Units for the Text Post-processing Phase of Automatic Transcription (in the Czech Language)....Pages 446-455 On the Impact of Annotation Errors on Unit-Selection Speech Synthesis....Pages 456-463 Analysis of the Influence of Speech Corpora in the PLDA Verification in the Task of Speaker Recognition....Pages 464-471 Adaptive Language Modeling with a Set of Domain Dependent Models....Pages 472-479 Robust Adaptation Techniques Dealing with Small Amount of Data....Pages 480-487 Language Modeling of Nonverbal Vocalizations in Spontaneous Speech....Pages 488-495 Acoustic Segmentation Using Group Delay Functions and Its Relevance to Spoken Keyword Spotting....Pages 496-504 Front Matter....Pages 403-403 An In-Car Speech Recognition System for Disabled Drivers....Pages 505-512 Captioning of Live TV Programs through Speech Recognition and Re-speaking....Pages 513-519 Investigation on Most Frequent Errors in Large-Scale Speech Recognition Applications....Pages 520-527 Neural Network Language Model with Cache....Pages 528-534 TENOR: A Lexical Normalisation Tool for Spanish Web 2.0 Texts....Pages 535-542 A Bilingual HMM-Based Speech Synthesis System for Closely Related Languages....Pages 543-550 The Role of Nasal Contexts on Quality of Vowel Concatenations....Pages 551-558 Analysis and Assessment of State Relevance in HMM-Based Feature Extraction Method....Pages 559-565 On the Impact of Non-speech Sounds on Speaker Recognition....Pages 566-572 Automatic Rating of Hoarseness by Text-based Cepstral and Prosodic Evaluation....Pages 573-580 Improving the Classification of Healthy and Pathological Continuous Speech....Pages 581-588 Front Matter....Pages 589-589 Using Foot-Syllable Grammars to Customize Speech Recognizers for Dialogue Systems....Pages 591-598 Coupled Pragmatic and Semantic Automata in Spoken Dialogue Management....Pages 599-606 Exploration of Metaphor and Affect Sensing Using Semantic Interpretation in an Intelligent Agent....Pages 607-615 Sentence Classification with Grammatical Errors and Those Out of Scope of Grammar Assumption for Dialogue-Based CALL Systems....Pages 616-623 Spoken Dialogue System Design in 3 Weeks....Pages 624-631 Integrating Dialogue Systems with Images....Pages 632-639 Natural Language Understanding: From Laboratory Predictions to Real Interactions....Pages 640-647 Unsupervised Clustering of Prosodic Patterns in Spontaneous Speech....Pages 648-655 Czech Expressive Speech Synthesis in Limited Domain....Pages 656-664 Front Matter....Pages 589-589 Aggression Detection in Speech Using Sensor and Semantic Information....Pages 665-672 Question Classification with Active Learning....Pages 673-680 2B$ – Testing Past Algorithms in Nowadays Web....Pages 681-688 Morphological Resources for Precise Information Retrieval....Pages 689-696 Back Matter....Pages -