Text, Speech and Dialogue

The Text, Speech and Dialogue (TSD) Conference 2002, it should be noticed, is now being held for the ?fth time and we are pleased to observe that in its short history it has turned out to be an international forum successfully intertwining the basic ?elds of NLP. It is our strong hope that the conference contributes to a better understanding between researchers from the various areas and promotes more intensive mutual cooperation. So far the communication between man and computers has displayed a one-way nature, humans have to know how the - chines work and only then can they "understand" them. The opposite, however, is still quite far from being real, our understanding of how our "user-friendly" computers can understand us humans is not deep enough yet. A lot of work has to be done both in the near and distant future. Let TSD 2002 be a modest contribution to this goal. The conference also serves well in its second purpose: to facilitate researchers meeting in the NLP ?eld from Western and Eastern Europe. Moreover, many participants now come from other parts of the world, thus making TSD a real crossroadsforresearchersintheNLParea. Thisvolumecontainstheproceedings of this conference held in Brno, September 9-12, 2002. We were honored to have as keynote speakers James Pustejovsky from Brandeis University, and Ronald Cole from the University of Colorado. We would like to thank all the Program Committee members and external reviewers for their conscientious and diligent reviewing work.

Inhalt

Text.- A Common Solution for Tokenization and Part-of-Speech Tagging.- Rule Parser for Arabic Stemmer.- Achieving an Almost Correct PoS-Tagged Corpus.- Evaluation of a Japanese Sentence Compression Method Based on Phrase Significance and Inter-Phrase Dependency.- User Query Understanding by the InBASE System as a Source for a Multilingual NL Generation Module.- The Role of WSD for Multilingual Natural Language Applications.- Gibbsian Context-Free Grammar for Parsing.- Cross-Language Access to Recorded Speech in the MALACH Project.- Using Salient Words to Perform Categorization of Web Sites.- Discourse-Semantic Analysis of Hungarian Sign Language.- Dependency Analyser Configurable by Measures.- The Generation and Use of Layer Information in Multilayered Extended Semantic Networks.- Filtering of Large Numbers of Unstructured Text Documents by the Developed Tool TEA.- Visualisation Techniques for Analysing Meaning.- Statistical Part-of-Speech Tagging for Classical Chinese.- Spanish Natural Language Interface for a Relational Database Querying System.- Word Sense vs. Word Domain Disambiguation: A Maximum Entropy Approach.- Exploiting Thesauri and Hierarchical Categories in Cross-Language Information Retrieval.- Valency Lexicon for Czech: From Verbs to Nouns.- Term Clustering Using a Corpus-Based Similarity Measure.- Word Sense Discrimination for Czech.- Tools for Semi-automatic Assignment of Czech Nouns to Declination Patterns.- Speech.- Automatic Lexical Stress Assignment of Unknown Words for Highly Inflected Slovenian Language.- German and Czech Speech Synthesis Using HMM-Based Speech Segment Database.- Comparison and Combination of Confidence Measures.- Strategies for Developing a Real-Time Continuous Speech Recognition System for Czech Language.- Comparative Study on Bigram Language Models for Spoken Czech Recognition.- Integration of Speech Recognition and Automatic Lip-Reading.- Utterance Verification Based on the Likelihood Distance to Alternative Paths.- Rejection Technique Based on the Mumble Model.- Efficient Noise Estimation and Its Application for Robust Speech Recognition.- AlfaNum System for Speech Synthesis in Serbian Language.- Speech Features Extraction Using Cone-Shaped Kernel Distribution.- Automatic Transcription of Czech Language Oral History in the MALACH Project: Resources and Initial Experiments.- On the First Greek-TTS Based on Festival Speech Synthesis.- An Analysis of Limited Domains for Speech Synthesis.- Advances in Very Low Bit Rate Speech Coding Using Recognition and Synthesis Techniques.- A Comparison of Different Approaches to Automatic Speech Segmentation.- Keyword Spotting Using Support Vector Machines.- Automatic Parameter Estimation for a Context-Independent Speech Segmentation Algorithm.- Phoneme Lattice Based A* Search Algorithm for Speech Recognition.- Heuristic and Statistical Methods for Speech/Non-speech Detector Design.- An Analysis of Conditional Responses in Dialogue.- Some Like It Gaussian. . ..- Kernel Springy Discriminant Analysis and Its Application to a Phonological Awareness Teaching System.- Large Vocabulary Speech Recognition of Slovenian Language Using Data-Driven Morphological Models.- Uniform Speech Recognition Platform for Evaluation of New Algorithms.- Speech Enhancement Using Mixtures of Gaussians for Speech and Noise.- Fitting German into N-Gram Language Models.- Audio Collections of Endangered Arctic Languages in the Russian Federation.- Dialogue.- Prosodic Classification of Offtalk: First Experiments.- Statistical Decision Making from Text and Dialogue Corpora for Effective Plan Recognition.- Natural Language Guided Dialogues for Accessing theWeb.- Evaluating a Probabilistic Dialogue Model for a Railway Information Task.- Applying Dialogue Constraints to the Understanding Process in a Dialogue System.- Evaluation of Prediction Methods Applied to an Inflected Language.- Knowledge Based Speech Interfacing for Handhelds.- Different Approaches to Build Multilingual Conversational Systems.- Strategies to Overcome Problematic Input in a Spanish Dialogue System.- Dialogue Systems and Planning.- A Flexible Framework for Evaluation of New Algorithms for Dialogue Systems.- From HTML to VoiceXML: A First Approach.- Voice Chat with a Virtual Character: The Good Soldier svejk Case Project.- Application of Spoken Dialogue Technology in a Medical Domain.- A Voice-Driven Web Browser for Blind People.- Enhancing Best Analysis Selection and Parser Comparison.