Frederick Jelinek, Jia Cui (auth.), Václav Matoušek, Pavel Mautner (eds.)3540746277, 9783540746270
The 80 revised full papers presented together with four invited papers were carefully reviewed and selected from 198 submissions. The papers present a wealth of state-of-the-art research results in the field of natural language processing with an emphasis on text, speech, and spoken dialogue ranging from theoretical and methodological issues to applications in various fields and with special focus on corpora, texts and transcription, speech analysis, recognition and synthesis, as well as their intertwining within NL dialogue systems.
Table of contents :
Front Matter….Pages –
Language Modeling with Linguistic Cluster Constraints….Pages 1-1
Some of Our Best Friends Are Statisticians….Pages 2-10
Some Special Problems of Speech Communication….Pages 11-13
Recent Advances in Spoken Language Understanding….Pages 14-14
Transformation-Based Tectogrammatical Dependency Analysis of English….Pages 15-22
Multilingual Name Disambiguation with Semantic Information….Pages 23-30
Inducing Classes of Terms from Text….Pages 31-38
Accurate Unlexicalized Parsing for Modern Hebrew….Pages 39-47
Disambiguation of the Neuter Pronoun and Its Effect on Pronominal Coreference Resolution….Pages 48-55
Constructing a Large Scale Text Corpus Based on the Grid and Trustworthiness….Pages 56-65
Disambiguating Hypernym Relations for Roget’s Thesaurus….Pages 66-75
Dependency and Phrasal Parsers of the Czech Language: A Comparison….Pages 76-84
Automatic Word Clustering in Russian Texts….Pages 85-91
Feature Engineering in Maximum Spanning Tree Dependency Parser….Pages 92-98
Automatic Selection of Heterogeneous Syntactic Features in Semantic Similarity of Polish Nouns….Pages 99-106
Bilingual News Clustering Using Named Entities and Fuzzy Similarity….Pages 107-114
Extractive Summarization of Broadcast News: Comparing Strategies for European Portuguese….Pages 115-122
On the Evaluation of Korean WordNet….Pages 123-130
An Adaptive Keyboard with Personalized Language-Based Features….Pages 131-138
An All-Path Parsing Algorithm for Constraint-Based Dependency Grammars of CF-Power….Pages 139-146
Word Distribution Based Methods for Minimizing Segment Overlaps….Pages 147-154
On the Relative Hardness of Clustering Corpora….Pages 155-161
Indexing and Retrieval Scheme for Content-Based Multimedia Applications….Pages 162-169
Automatic Diacritic Restoration for Resource-Scarce Languages….Pages 170-179
Lexical and Perceptual Grounding of a Sound Ontology….Pages 180-187
Named Entities in Czech: Annotating Data and Developing NE Tagger….Pages 188-195
Identifying Expressions of Emotion in Text….Pages 196-205
ECAF: Authoring Language for Embodied Conversational Agents….Pages 206-213
Dynamic Adaptation of Language Models in Speech Driven Information Retrieval….Pages 214-221
Whitening-Based Feature Space Transformations in a Speech Impediment Therapy System….Pages 222-229
Spanish-Basque Parallel Corpus Structure: Linguistic Annotations and Translation Units….Pages 230-237
An Automatic Version of the Post-Laryngectomy Telephone Test….Pages 238-245
Speaker Normalization Via Springy Discriminant Analysis and Pitch Estimation….Pages 246-253
A Study on Speech with Manifest Emotions….Pages 254-261
Speech Recognition Supported by Prosodic Information for Fixed Stress Languages….Pages 262-269
TRAP-Based Techniques for Recognition of Noisy Speech….Pages 270-277
Intelligibility Is More Than a Single Word: Quantification of Speech Intelligibility by ASR and Prosody….Pages 278-285
Appositions Versus Double Subject Sentences – What Information the Speech Analysis Brings to a Grammar Debate….Pages 286-293
Automatic Evaluation of Pathologic Speech – from Research to Routine Clinical Use….Pages 294-301
The LIA Speech Recognition System: From 10xRT to 1xRT….Pages 302-308
Logic-Based Rhetorical Structuring for Natural Language Generation in Human-Computer Dialogue….Pages 309-317
Text-Independent Speaker Identification Using Temporal Patterns….Pages 318-325
Recording and Annotation of Speech Corpus for Czech Unit Selection Speech Synthesis….Pages 326-333
Sk-ToBI Scheme for Phonological Prosody Annotation in Slovak….Pages 334-341
Towards Automatic Transcription of Large Spoken Archives in Agglutinating Languages – Hungarian ASR for the MALACH Project….Pages 342-349
Non-uniform Speech/Audio Coding Exploiting Predictability of Temporal Evolution of Spectral Envelopes….Pages 350-357
Filled Pauses in Speech Synthesis: Towards Conversational Speech….Pages 358-365
Exploratory Analysis of Word Use and Sentence Length in the Spoken Dutch Corpus….Pages 366-373
Design of Tandem Architecture Using Segmental Trend Features….Pages 374-381
An Automatic Retraining Method for Speaker Independent Hidden Markov Models….Pages 382-389
User Modeling to Support the Development of an Auditory Help System….Pages 390-397
Fast Discriminant Training of Semi-continuous HMM….Pages 398-405
Speech/Music Discrimination Using Mel-Cepstrum Modulation Energy….Pages 406-414
Parameterization of the Input in Training the HVS Semantic Parser….Pages 415-422
A Comparison Using Different Speech Parameters in the Automatic Emotion Recognition Using Feature Subset Selection Based on Evolutionary Algorithms….Pages 423-430
Benefit of Maximum Likelihood Linear Transform (MLLT) Used at Different Levels of Covariance Matrices Clustering in ASR Systems….Pages 431-438
Information Retrieval Test Collection for Searching Spontaneous Czech Speech….Pages 439-446
Inter-speaker Synchronization in Audiovisual Database for Lip-Readable Speech to Animation Conversion….Pages 447-454
Constructing Empirical Models for Automatic Dialog Parameterization….Pages 455-463
The Effect of Lexicon Composition in Pronunciation by Analogy….Pages 464-471
Festival-si: A Sinhala Text-to-Speech System….Pages 472-479
Voice Conversion Based on Probabilistic Parameter Transformation and Extended Inter-speaker Residual Prediction….Pages 480-487
Automatic Czech – Sign Speech Translation….Pages 488-495
Maximum Likelihood and Maximum Mutual Information Training in Gender and Age Recognition System….Pages 496-501
Pitch Marks at Peaks or Valleys?….Pages 502-507
Quality Deterioration Factors in Unit Selection Speech Synthesis….Pages 508-515
Topic-Focus Articulation Algorithm on the Syntax-Prosody Interface of Romanian….Pages 516-523
Translation and Conversion for Czech Sign Speech Synthesis….Pages 524-531
A Wizard-of-Oz System Evaluation Study….Pages 532-539
New Measures for Open-Domain Question Answering Evaluation Within a Time Constraint….Pages 540-547
A Methodology for Domain Dialogue Engineering with the Midiki Dialogue Manager….Pages 548-555
The Intonational Realization of Requests in Polish Task-Oriented Dialogues….Pages 556-563
Analysis of Changes in Dialogue Rhythm Due to Dialogue Acts in Task-Oriented Dialogues….Pages 564-573
Recognition and Understanding Simulation for a Spoken Dialog Corpus Acquisition….Pages 574-581
First Approach in the Development of Multimedia Information Retrieval Resources for the Basque Context….Pages 582-590
The Weakest Link….Pages 591-598
A Spoken Dialog System for Chat-Like Conversations Considering Response Timing….Pages 599-606
Digitisation and Automatic Alignment of the DIALOG Corpus: A Prosodically Annotated Corpus of Czech Television Debates….Pages 607-612
Setting Layout in Dialogue Generating Web Pages….Pages 613-620
Graph-Based Answer Fusion in Multilingual Question Answering….Pages 621-629
Using Query-Relevant Documents Pairs for Cross-Lingual Information Retrieval….Pages 630-637
Detection of Dialogue Acts Using Perplexity-Based Word Clustering….Pages 638-643
Dialogue Management for Intelligent TV Based on Statistical Learning Method….Pages 644-652
Multiple-Taxonomy Question Classification for Category Search on Faceted Information….Pages 653-660
Indexing and Retrieval Scheme for Content-Based Multimedia Applications….Pages 661-661
Back Matter….Pages –
Reviews
There are no reviews yet.