The annual Text, Speech and Dialogue Conference (TSD), which originated in 1998, is now coming to the end of its ?rst decade. During this time almost 400 authors from 36 countries have contributed to the proceedings. TSD constitutes a recognized forum for the presentation and discussion of state-of-the-art technology and recent achievements in the ?eld of natural language processing. It has become an interdisciplinary forum, interweaving the themes of speech technology and language processing. The conference attracts researchers not only from Central and Eastern Europe but also from other parts of the world. Indeed, one of its goals has always been to bring together NLP researchers with different interests from different parts of the world and to promote their mutual cooperation. This volume containsthe proceedings of the Ninth TSD Conference, held in Brno, Czech Republic in September 2006. Following the review process, 87 papers were accepted out of 175 submitted, an acceptance rate of 49.7%. The number of the submissions this year was the highest so far. We would like to thank all the authors for the efforts they put into their submissions and the members of the Program Committee and reviewers who did a wonderful job helping us to select the most appropriate papers. We are also grateful to the invited speakers for their contribution. Their talks provided insight into important issues, applications and techniques related to the conference topics.
Author(s): Eduard Hovy (auth.), Petr Sojka, Ivan Kopeček, Karel Pala (eds.)
Series: Lecture Notes in Computer Science 4188 : Lecture Notes in Artificial Intelligence
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2006
Language: English
Pages: 721
Tags: Artificial Intelligence (incl. Robotics); Information Storage and Retrieval; Information Systems Applications (incl.Internet); Language Translation and Linguistics
Front Matter....Pages -
Front Matter....Pages 1-1
Learning by Reading: An Experiment in Text Analysis....Pages 3-12
Depth of Feelings: Alternatives for Modeling Affect in User Models....Pages 13-18
Front Matter....Pages 19-19
The Lexico-Semantic Annotation of PDT: Some Results, Problems and Solutions....Pages 21-28
Czech Verbs of Communication and the Extraction of Their Frames....Pages 29-36
Featuring of Sex-Dependent Nouns in Databases Oriented to European Languages....Pages 37-44
On the Behavior of SVM and Some Older Algorithms in Binary Text Classification Tasks....Pages 45-52
A Knowledge Based Strategy for Recognising Textual Entailment....Pages 53-60
Paragraph-Level Alignment of an English-Spanish Parallel Corpus of Fiction Texts Using Bilingual Dictionaries....Pages 61-67
Some Methods of Describing Discontinuity in Polish and Their Cost-Effectiveness....Pages 69-77
Exploitation of the VerbaLex Verb Valency Lexicon in the Syntactic Analysis of Czech....Pages 79-85
Hungarian-English Machine Translation Using GenPar....Pages 87-94
Combining Czech Dependency Parsers....Pages 95-102
Processing Korean Numeral Classifier Constructions in a Typed Feature Structure Grammar....Pages 103-110
Parsing Head Internal and External Relative Clause Constructions in Korean....Pages 111-117
A Hybrid Model for Extracting Transliteration Equivalents from Parallel Corpora....Pages 119-126
Sentence Compression Using Statistical Information About Dependency Path Length....Pages 127-134
Transformation-Based Tectogrammatical Analysis of Czech....Pages 135-142
The Effect of Semantic Knowledge Expansion to Textual Entailment Recognition....Pages 143-150
Segmentation of Complex Sentences....Pages 151-158
Enhanced Centroid-Based Classification Technique by Filtering Outliers....Pages 159-163
Front Matter....Pages 19-19
Multilingual News Document Clustering: Two Algorithms Based on Cognate Named Entities....Pages 165-172
A Study of the Influence of PoS Tagging on WSD....Pages 173-179
Annotation of Temporal Relations Within a Discourse....Pages 181-188
Applying RST Relations to Semantic Search....Pages 189-196
Data-Driven Part-of-Speech Tagging of Kiswahili....Pages 197-204
Hand-Written and Automatically Extracted Rules for Polish Tagger....Pages 205-212
Effective Architecture of the Polish Tagger....Pages 213-220
Synthesis of Czech Sentences from Tectogrammatical Trees....Pages 221-228
ASeMatch: A Semantic Matching Method....Pages 229-235
Extensive Study on Automatic Verb Sense Disambiguation in Czech....Pages 237-244
Semantic Representation of Events: Building a Semantic Primes Component....Pages 245-252
Cascaded Grammatical Relation-Driven Parsing Using Support Vector Machines....Pages 253-259
Building Korean Classifier Ontology Based on Korean WordNet....Pages 261-268
Exploiting the Translation Context for Multilingual WSD....Pages 269-276
Post-annotation Checking of Prague Dependency Treebank 2.0 Data....Pages 277-284
Language Modelling with Dynamic Syntax....Pages 285-292
Using Word Sequences for Text Summarization....Pages 293-300
Exploration of Coreference Resolution: The ACE Entity Detection and Recognition Task....Pages 301-308
Parsing with Oracle....Pages 309-316
Front Matter....Pages 317-317
Evaluating Language Models Within a Predictive Framework: An Analysis of Ranking Distributions....Pages 319-326
Front Matter....Pages 317-317
Another Look at the Data Sparsity Problem....Pages 327-334
Syllable-Based Recognition Unit to Reduce Error Rate for Korean Phones, Syllables and Characters....Pages 335-341
Recognizing Connected Digit Strings Using Neural Networks....Pages 343-350
Indexing and Search Methods for Spoken Documents....Pages 351-358
Analysis of HMM Temporal Evolution for Automatic Speech Recognition and Verification....Pages 359-366
Corpus-Based Unit Selection TTS for Hungarian....Pages 367-373
Automated Mark Up of Affective Information in English Texts....Pages 375-382
First Steps Towards New Czech Voice Conversion System....Pages 383-390
Are Morphosyntactic Taggers Suitable to Improve Automatic Transcription?....Pages 391-398
Fast Speaker Adaptation Using Multi-stream Based Eigenvoice in Noisy Environments....Pages 399-406
Phonetic Question Generation Using Misrecognition....Pages 407-414
Speech Driven Facial Animation Using HMMs in Basque....Pages 415-422
Comparing B-Spline and Spline Models for F0 Modelling....Pages 423-430
Environmental Adaptation with a Small Data Set of the Target Domain....Pages 431-437
Current State of Czech Text-to-Speech System ARTIC....Pages 439-446
Automatic Korean Phoneme Generation Via Input-Text Preprocessing and Disambiguation....Pages 447-454
Robust Speech Detection Based on Phoneme Recognition Features....Pages 455-462
Composite Decision by Bayesian Inference in Distant-Talking Speech Recognition....Pages 463-470
Speech Coding Based on Spectral Dynamics....Pages 471-478
Detecting Broad Phonemic Class Boundaries from Greek Speech in Noise Environments....Pages 479-484
Front Matter....Pages 317-317
A System for Information Retrieval from Large Records of Czech Spoken Data....Pages 485-492
A Structure of Expert System for Speaker Verification....Pages 493-500
Automatic Online Subtitling of the Czech Parliament Meetings....Pages 501-508
Character Identity Expression in Vocal Performance of Traditional Puppeteers....Pages 509-516
A Dissonant Frequency Filtering for Enhanced Clarity of Husky Voice Signals....Pages 517-522
Post-processing of Automatic Segmentation of Speech Using Dynamic Programming....Pages 523-530
Diphones vs. Triphones in Czech Unit Selection TTS....Pages 531-538
Silence/Speech Detection Method Based on Set of Decision Graphs....Pages 539-546
Prosodic Cues for Automatic Phrase Boundary Detection in ASR....Pages 547-554
Dynamic Bayesian Networks for Language Modeling....Pages 555-562
Front Matter....Pages 563-563
Feature Subset Selection Based on Evolutionary Algorithms for Automatic Emotion Recognition in Spoken Spanish and Standard Basque Language....Pages 565-572
Two-Dimensional Visual Language Grammar....Pages 573-580
Are You Looking at Me, Are You Talking with Me: Multimodal Classification of the Focus of Attention....Pages 581-588
Visualization of Voice Disorders Using the Sammon Transform....Pages 589-596
Task Switching in Audio Based Systems....Pages 597-604
Use of Negative Examples in Training the HVS Semantic Model....Pages 605-612
Czech-Sign Speech Corpus for Semantic Based Machine Translation....Pages 613-620
Processing of Requests in Estonian Institutional Dialogues: Corpus Analysis....Pages 621-628
Using Prosody for Automatic Sentence Segmentation of Multi-party Meetings....Pages 629-636
Simple Method of Determining the Voice Similarity and Stability by Analyzing a Set of Very Short Sounds....Pages 637-643
Front Matter....Pages 563-563
Visualization of Prosodic Knowledge Using Corpus Driven MEMOInt Intonation Modelling....Pages 645-652
Automatic Annotation of Dialogues Using n -Grams....Pages 653-660
PPChecker: Plagiarism Pattern Checker in Document Copy Detection....Pages 661-667
Segmental Duration Modelling in Turkish....Pages 669-676
A Pattern-Based Methodology for Multimodal Interaction Design....Pages 677-686
A Pattern Learning Approach to Question Answering Within the Ephyra Framework....Pages 687-694
Explicative Document Reading Controlled by Non-speech Audio Gestures....Pages 695-702
Hybrid Neural Network Design and Implementation on FPGA for Infant Cry Recognition....Pages 703-709
Speech and Sound Use in a Remote Monitoring System for Health Care....Pages 711-718
Back Matter....Pages -
