Invited Talks -- Research Issues for the Next Generation Spoken Dialogue Systems -- Data-Driven Analysis of Speech -- Towards a Road Map for Machine Translation Research -- The Prague Dependency Treebank: Crossing the Sentence Boundary -- Text -- Tiered Tagging and Combined Language Models Classifiers -- Syntactic Tagging: Procedure for the Transition from the Analytic to the Tectogrammatical Tree Structures -- Information, Language, Corpus and Linguistics -- Prague Dependency Treebank: Restoration of Deletions -- Some Types of Syntactic Ambiguity; How to Treat Them in an Automatic Procedure -- Semantic Annotation of (Czech) Corpus Texts -- The General Principles of the Diachronic Part of the Czech National Corpus -- Performing Adaptive Morphological Analysis Using Internet Resources -- Automatic Text-to-Speech Alignment: Aspects of Robustification -- Czech Translation of G. Orwell’s ‘1984’: Morphology and Syntactic Patterns in the Corpus -- Handling Word Order in a Multilingual System for Generation of Instructions -- Text Structuring in a Multilingual System for Generation of Instructions -- Leveraging Syntactic Information for Text Normalization -- Automatic Structuring of Written Texts -- Implementation of Efficient and Portable Parser for Czech -- Word Sense Disambiguation of Czech Texts -- The Acquisition of Some Lexical Constraints from Corpora -- Run-Time Extensible (Semi-)Top-Down Parser -- Enhancing Readability of Automatic Summaries by Using Schemas -- Use of a Weighted Topic Hierarchy for Document Classification -- Speech -- Remarks on Sentence Prosody and Topic-Focus Articulation -- Speech Recognition Using Elman Neural Networks -- Use of Hidden Markov Models for Evaluation of Russian Digits Pronunciation by the Foreigners -- Allophone-Based Concatenative Speech Synthesis System for Russian -- Intonation Questions in English and Armenian: Results of the Perceptual Study -- Methods of Sentences Selection for Read-Speech Corpus Design -- Speaker Identification Using Discriminative Centroids Weighting — A Growing Cell Structure Approach -- Speech Analysis and Recognition Synchronised by One-Quasiperiodical Segmentation -- Spanish Phoneme Classification by Means of a Hierarchy of Kohonen Self-Organizing Maps -- Information Theoretic Based Segments for Language Identification -- Fast and Robust Features for Prosodic Classification? -- A Segment Based Approach for Prosodic Boundary Detection? -- Speech Recognition and Syllable Segments -- Text Preprocessing for Czech Speech Synthesis -- MLPs and Mixture Models for the Estimation of the Posterior Probabilities of Class Membership -- A Simple Spanish Part of Speech Tagger for Detection and Correction of Accentuation Error -- Slovene Interactive Text-to-Speech Evaluation Site — SITES -- Developing HMM-Based Recognizers with ESMERALDA -- Large Vocabulary Speech Recognition for Read and Broadcast Czech -- Rules for Automatic Grapheme-to-Allophone Transcription in Slovene -- Speech Segmentation Aspects of Phone Transition Acoustical Modelling -- Context Dependent Phoneme Recognition -- State-Space Model Based Labeling of Speech Signals -- Very Low Bit Rate Speech Coding: Comparison of Data-Driven Units with Syllable Segments -- Storing Prosody Attributes of Spontaneous Speech -- Dialogue -- An Overview of the State of the Art of Coding Schemes for Dialogue Act Annotation -- Structural and Semantic Dialogue Filters -- A Retrieval System of Broadcast News Speech Documents through Keyboard and Voice -- Situations in Dialogs -- Components for Building an Automatic Voice-Dialogue Telephone System -- Modeling of the Information Retrieval Dialogue Systems -- Improvement of the Recognition Rate of Spoken Queries to the Dialogue System -- Analysis of Different Dialog Strategies in the Slovenian Spoken Dialog System -- Posters -- Dispersion of Words in a Language Corpus -- Corpus-Based Rules for Czech Verb Discontinuous Constituents -- Automatic Modelling of Regional Pronunciation Variation for Russian -- Experiments Regarding the Superposition of Emotional Features on Neutral Korean Speech -- Modeling Cue Phrases in Turkish: A Case Study -- Speaker Identification Based on Vector Quantization -- Robustness in Tabular Deduction for Multimodal Logical Grammar — Part 1 -- Classifying Visemes for Automatic Lipreading -- Semantic Inference in the Human-Machine Communication -- Playing with RST: Two Algorithms for the Automated Manipulation of Discourse Trees -- Another Step in the Modeling of Basque Intonation: Bermeo -- Electronic Dictionaries: For Both Humans and Computers -- Statistical Evaluation of Similarity Measures on Multi-lingual Text Corpora -- Document Title Patterns in Information Retrieval -- Statistical Approach to the Automatic Synthesis of Czech Speech -- Language Model Representations for the GOPOLIS Database -- Recognition of Alkohol Influence on Speech -- Recording of Czech and Slovak Telephone Databases within SpeechDat-E -- Pragmatic Features of the Electronic Discourse in the Internet.