Text, Speech and Dialogue: 9th International Conference, TSD 2006, Brno, Czech Republic, September 11-15, 2006, Proceedings

ISBN-13: 9783540390909 / Angielski / Miękka / 2006 / 721 str.

Petr Sojka;Ivan Kopecek;Karel Pala

Opis

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.

Spis treści

Invited Papers.- Learning by Reading: An Experiment in Text Analysis.- Depth of Feelings: Alternatives for Modeling Affect in User Models.- Text.- The Lexico-Semantic Annotation of PDT: Some Results, Problems and Solutions.- Czech Verbs of Communication and the Extraction of Their Frames.- Featuring of Sex-Dependent Nouns in Databases Oriented to European Languages.- On the Behavior of SVM and Some Older Algorithms in Binary Text Classification Tasks.- A Knowledge Based Strategy for Recognising Textual Entailment.- Paragraph-Level Alignment of an English-Spanish Parallel Corpus of Fiction Texts Using Bilingual Dictionaries.- Some Methods of Describing Discontinuity in Polish and Their Cost-Effectiveness.- Exploitation of the VerbaLex Verb Valency Lexicon in the Syntactic Analysis of Czech.- Hungarian-English Machine Translation Using GenPar.- Combining Czech Dependency Parsers.- Processing Korean Numeral Classifier Constructions in a Typed Feature Structure Grammar.- Parsing Head Internal and External Relative Clause Constructions in Korean.- A Hybrid Model for Extracting Transliteration Equivalents from Parallel Corpora.- Sentence Compression Using Statistical Information About Dependency Path Length.- Transformation-Based Tectogrammatical Analysis of Czech.- The Effect of Semantic Knowledge Expansion to Textual Entailment Recognition.- Segmentation of Complex Sentences.- Enhanced Centroid-Based Classification Technique by Filtering Outliers.- Multilingual News Document Clustering: Two Algorithms Based on Cognate Named Entities.- A Study of the Influence of PoS Tagging on WSD.- Annotation of Temporal Relations Within a Discourse.- Applying RST Relations to Semantic Search.- Data-Driven Part-of-Speech Tagging of Kiswahili.- Hand-Written and Automatically Extracted Rules for Polish Tagger.- Effective Architecture of the Polish Tagger.- Synthesis of Czech Sentences from Tectogrammatical Trees.- ASeMatch: A Semantic Matching Method.- Extensive Study on Automatic Verb Sense Disambiguation in Czech.- Semantic Representation of Events: Building a Semantic Primes Component.- Cascaded Grammatical Relation-Driven Parsing Using Support Vector Machines.- Building Korean Classifier Ontology Based on Korean WordNet.- Exploiting the Translation Context for Multilingual WSD.- Post-annotation Checking of Prague Dependency Treebank 2.0 Data.- Language Modelling with Dynamic Syntax.- Using Word Sequences for Text Summarization.- Exploration of Coreference Resolution: The ACE Entity Detection and Recognition Task.- Parsing with Oracle.- Speech.- Evaluating Language Models Within a Predictive Framework: An Analysis of Ranking Distributions.- Another Look at the Data Sparsity Problem.- Syllable-Based Recognition Unit to Reduce Error Rate for Korean Phones, Syllables and Characters.- Recognizing Connected Digit Strings Using Neural Networks.- Indexing and Search Methods for Spoken Documents.- Analysis of HMM Temporal Evolution for Automatic Speech Recognition and Verification.- Corpus-Based Unit Selection TTS for Hungarian.- Automated Mark Up of Affective Information in English Texts.- First Steps Towards New Czech Voice Conversion System.- Are Morphosyntactic Taggers Suitable to Improve Automatic Transcription?.- Fast Speaker Adaptation Using Multi-stream Based Eigenvoice in Noisy Environments.- Phonetic Question Generation Using Misrecognition.- Speech Driven Facial Animation Using HMMs in Basque.- Comparing B-Spline and Spline Models for F0 Modelling.- Environmental Adaptation with a Small Data Set of the Target Domain.- Current State of Czech Text-to-Speech System ARTIC.- Automatic Korean Phoneme Generation Via Input-Text Preprocessing and Disambiguation.- Robust Speech Detection Based on Phoneme Recognition Features.- Composite Decision by Bayesian Inference in Distant-Talking Speech Recognition.- Speech Coding Based on Spectral Dynamics.- Detecting Broad Phonemic Class Boundaries from Greek Speech in Noise Environments.- A System for Information Retrieval from Large Records of Czech Spoken Data.- A Structure of Expert System for Speaker Verification.- Automatic Online Subtitling of the Czech Parliament Meetings.- Character Identity Expression in Vocal Performance of Traditional Puppeteers.- A Dissonant Frequency Filtering for Enhanced Clarity of Husky Voice Signals.- Post-processing of Automatic Segmentation of Speech Using Dynamic Programming.- Diphones vs. Triphones in Czech Unit Selection TTS.- Silence/Speech Detection Method Based on Set of Decision Graphs.- Prosodic Cues for Automatic Phrase Boundary Detection in ASR.- Dynamic Bayesian Networks for Language Modeling.- Dialogue.- Feature Subset Selection Based on Evolutionary Algorithms for Automatic Emotion Recognition in Spoken Spanish and Standard Basque Language.- Two-Dimensional Visual Language Grammar.- Are You Looking at Me, Are You Talking with Me: Multimodal Classification of the Focus of Attention.- Visualization of Voice Disorders Using the Sammon Transform.- Task Switching in Audio Based Systems.- Use of Negative Examples in Training the HVS Semantic Model.- Czech-Sign Speech Corpus for Semantic Based Machine Translation.- Processing of Requests in Estonian Institutional Dialogues: Corpus Analysis.- Using Prosody for Automatic Sentence Segmentation of Multi-party Meetings.- Simple Method of Determining the Voice Similarity and Stability by Analyzing a Set of Very Short Sounds.- Visualization of Prosodic Knowledge Using Corpus Driven MEMOInt Intonation Modelling.- Automatic Annotation of Dialogues Using n-Grams.- PPChecker: Plagiarism Pattern Checker in Document Copy Detection.- Segmental Duration Modelling in Turkish.- A Pattern-Based Methodology for Multimodal Interaction Design.- A Pattern Learning Approach to Question Answering Within the Ephyra Framework.- Explicative Document Reading Controlled by Non-speech Audio Gestures.- Hybrid Neural Network Design and Implementation on FPGA for Infant Cry Recognition.- Speech and Sound Use in a Remote Monitoring System for Health Care.