Text, Speech and Dialogue

1. Front Matter

   PDF

2. Invited Talks

   1. Language Modeling Experiments with Random Forests

      • Frederick Jelinek

      Pages 1-1

   2. The Role of Speech in Multimodal Human-Computer Interaction

      • Hynek Hermansky, Petr Fousek, Mikko Lehtonen

      Pages 2-8

   3. Why Is the Recognition of Spontaneous Speech so Hard?

      • Sadaoki Furui, Masanobu Nakamura, Tomohisa Ichiba, Koji Iwano

      Pages 9-22

   4. On the Acoustic Components in Multimedia Presentations

      • Klaus Fellbaum, Bettina Ketzmerick

      Pages 23-32

   5. Fusing Data Streams in Continuous Audio-Visual Speech Recognition

      • Leon J. M. Rothkrantz, Jacek C. Wojdeł, Pascal Wiggers

      Pages 33-44

   6. Speech Based User Interface for Users with Special Needs

      • Pavel Slavík, Vladislav Němec, Adam J. Sporka

      Pages 45-55

3. Text

   1. Automatic Construction of a Valency Lexicon of Czech Adjectives

      • Drahomíra “Johanka” Doležalová

      Pages 56-60

   2. WebTranscribe – An Extensible Web-Based Speech Annotation Framework

      • Christoph Draxler

      Pages 61-68

   3. Learning Syntactic Patterns Using Boosting and Other Classifier Combination Schemas

      • András Hócza, László Felföldi, András Kocsor

      Pages 69-76

   4. Text Classification with Tournament Methods

      • Louise Guthrie, Wei Liu, Yunqing Xia

      Pages 77-84

   5. New Meta-grammar Constructs in Czech Language Parser synt

      • Aleš Horák, Vladimír Kadlec

      Pages 85-92

   6. Anaphora in Czech: Large Data and Experiments with Automatic Anaphora Resolution

      • Lucie Kučová, Zdeněk Žabokrtský

      Pages 93-98

   7. Valency Lexicon of Czech Verbs VALLEX: Recent Experiments with Frame Disambiguation

      • Markéta Lopatková, Ondřej Bojar, Jiří Semecký, Václava Benešová, Zdeněk Žabokrtský

      Pages 99-106

   8. AARLISS – An Algorithm for Anaphora Resolution in Long-Distance Inter Sentential Scenarios

      • Miroslav Martinovic, Anthony Curley, John Gaskins

      Pages 107-114

   9. Detection and Correction of Malapropisms in Spanish by Means of Internet Search

      • Igor A. Bolshakov, Sofia N. Galicia-Haro, Alexander Gelbukh

      Pages 115-122

   10. The Szeged Treebank

       • Dóra Csendes, János Csirik, Tibor Gyimóthy, András Kocsor

       Pages 123-131

   11. Automatic Lemmatizer Construction with Focus on OOV Words Lemmatization

       • Jakub Kanis, Luděk Müller

       Pages 132-139

   12. Modeling Syntax of Free Word-Order Languages: Dependency Analysis by Reduction

       • Markéta Lopatková, Martin Plátek, Vladislav Kuboň

       Pages 140-147

   13. Morphological Meanings in the Prague Dependency Treebank 2.0

       • Magda Razímová, Zdeněk Žabokrtský

       Pages 148-155

TheInternationalConferenceTSD 2005,the8theventin theseriesonText,Speech,and Dialogue, which originated in 1998, presented state-of-the-art technology and recent achievements in the ?eld of natural language processing. It declared its intent to be an interdisciplinary forum, intertwining research in speech and language processing with its applications in everyday practice. We feel that the mixture of different approaches and applications offered a great opportunity to get acquainted with the current act- ities in all aspects of language communication and to witness the amazing vitality of researchers from developing countries too. The ?nancial support of the ISCA (Inter- tional Speech Communication Association) enabled the wide attendance of researchers from all active regions of the world. Thisyear’sconferencewaspartiallyorientedtowardsmulti-modalhuman-computer interaction (HCI), which can be seen as the most attractive topic of HCI at the present time. In this way, we are involved in a rich complex of communicative activity, facial expressions, hand gestures, direction of gaze, to name but the most obvious ones. The interpretationof each user utterancedependson the context,prosody,facial expressions (e. g. brows raised, brows and gaze both raised) and gestures. Hearers have to adapt to the speaker (e. g. maintainingthe theme of the conversation,smiling etc. ). Research into the interaction of these channels is however limited, often focusing on the interaction between a pair of channels. Six signi?cant scienti?c results achieved in this area in the USA, Japan, Switzerland, Germany, The Netherlands, and the Czech Republic were presented by keynote speakers in special plenary sessions. Further, approx.

• algorithms
• classification
• learning
• natural language
• natural language processing
• semantic web
• verification

• Department of Computer Science, University of West Bohemia in Pilsen, Plzen, Czech Republic

  Václav Matoušek, Pavel Mautner, Tomáš Pavelka

Policies and ethics