Text, Speech, and Dialogue

This book constitutes the refereed proceedings of the 21st International Conference on Text, Speech, and Dialogue, TSD 2018, held in Brno, Czech Republic, in September 2018. The 56 regular papers were carefully reviewed and selected from numerous submissions. They focus on topics such as corpora and language resources, speech recognition, tagging, classification and parsing of text and speech, speech and spoken language generation, semantic processing of text and search, integrating applications of text and speech processing, machine translation, automatic dialogue systems, multimodal techniques and modeling.

Inhalt

Minsky, Chomsky & Deep Nets.- Leolani: a Reference Machine with a Theory of Mind for Social Communication.- Speech Analytics for Medical Applications.- Sentiment Attitudes and Their Extraction from Analytical Texts.- Prefixal Morphemes of Czech Verbs.- LDA in Character-LSTM-CRF Named Entity Recognition.- Lexical Stress-Based Authorship Attribution with Accurate Pronunciation Patterns Selection.- Idioms Modeling in a Computer Ontology as a Morphosyntactic Disambiguation Strategy (the Case of Tibetan Corpus of Grammar Treatises) .- Adjusting Machine Translation Datasets for Document-Level Cross-Language Information Retrieval: Methodology.- Deriving Enhanced Universal Dependencies from a Hybrid Dependency-Constituency Treebank.- Adaptation of Algorithms for Medical Information Retrieval for Working on Russian-Language Text Content.- CoRTE: A Corpus of Recognizing Textual Entailment Data Annotated for Coreference and Bridging Relations.- Evaluating Distributional Features for MultiwordExpression Recognition.- Manócska: A Unified Verb Frame Database for Hungarian.- Improving Part-of-Speech Tagging by Meta-Learning.- Identifying and Linking Participant Mentions in Legal Court Judgments.- Building the Tatar-Russian NMT System.- Annotated Clause Boundaries' Influence on Parsing Results.- Morphological Analyzer for the Tunisian Dialect.- Morphosyntactic Disambiguation and Segmentation for Historical Polish with Graph-Based Conditional Random Fields.- Do We Need Word Sense Disambiguation for LCM Tagging? .- Generation of Arabic Broken Plural within LKB.- Czech Dataset for Semantic Textual Similarity.- A Dataset and a Novel Neural Approach for Optical Gregg Shorthand Recognition.- A Lattice Based Algebraic Model for Verb Centered Constructions.- Annotated Corpus of Czech Case Law for Reference Recognition Tasks.- Recognition of the Logical Structure of Arabic Newspaper Pages.- A Cross-Lingual Approach for Building Multilingual Sentiment Lexicons.- Semantic Question Matching in Data Constrained Environment.- Morphological and Language-Agnostic Word Segmentation for NMT.- Multi-task Projected Embedding for Igbo.- Corpus Annotation Pipeline for Non-standard Texts.- Recognition of OCR Invoice Metadata Block Types.- Automatic Evaluation of Synthetic Speech Quality by a System Based on Statistical Analysis.- Robust Recognition of Conversational Telephone Speech via Multi-Condition Training and Data Augmentation.- Online LDA-Based Language Model Adaptation.- On the Extension of the Formal Prosody Model for TTS.- F0 Post-Stress Rise Trends Consideration in Unit Selection TTS.- Current State of Text-to-Speech System ARTIC: A Decade of Research on the Field of Speech Technologies.- Semantic Role Labeling of Speech Transcripts without Sentence Boundaries.- Voice Control in a Real Flight Deck Environment.- Data Augmentation and Teacher-Student Training for LF-MMI Based Robust Speech Recognition.- Using Anomaly Detection for Fine Tuning of Formal Prosodic Structuresin Speech Synthesis.- The Influence of Errors in Phonetic Annotations on Performance of Speech Recognition System.- Deep Learning and Online Speech Activity Detection for Czech Radio Broadcasting.- A Survey of Recent DNN Architectures on the TIMIT Phone Recognition Task.- WaveNet-Based Speech Synthesis Applied to Czech: A Comparison with the Traditional Synthesis Methods.- Phonological Posteriors and GRU Recurrent Units to Assess Speech.-Impairments of Patients with Parkinson's Disease.- Phonological i-Vectors to Detect Parkinson's Disease.- Subtext Word Accuracy and Prosodic Features for Automatic Intelligibility Assessment.- Prosodic Features' Criterion For Hebrew.- The Retention Effect of Learning Grammatical Patterns Implicitly Using Joining-in-Type Robot-Assisted Language-Learning System.- Learning to Interrupt the User at the Right Time in Incremental Dialogue Systems.- Towards a French Smart-Home Voice Command Corpus: Design and NLU Experiments.- Classification of Formal and Informal Dialogues Based on Emotion Recognition Features.