Umfang:
1 Online-Ressource(XV, 540 p. 102 illus., 79 illus. in color.)
Ausgabe:
1st ed. 2022.
ISBN:
9783031162701
Serie:
Lecture Notes in Artificial Intelligence 13502
Inhalt:
Evaluating Attribution Methods for Explainable NLP with Transformers -- Sido DaFNeGE: Dataset of French Newsletters with Graph Representation and Embedding -- ANTILLES: An Open French Linguistically Enriched Part-of-Speech Corpus -- Statistical and Neural Methods for Cross-lingual Entity Label Mapping in Knowledge Graphs -- Quality Assessment of Subtitles – Challenges and Strategies -- Computational Approaches for Understanding Semantic Constraints on Two-termed Coordination Structures -- Review of Practices of Collecting and Annotating Texts in the Learner Corpus REALEC -- New Language Identification and Sentiment Analysis Modules for Social Media Communication -- Identification of Metaphorical Collocations in Different Languages – Similarities and Differences -- Automatic Grammar Correction of Commas in Czech Written Texts: Comparative Study -- Linear Transformations for Cross-lingual Sentiment Analysis -- TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models -- Use of Machine Learning Methods in the Assessment of Programming Assignments -- Ontology-Aware Biomedical Relation Extraction -- Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising -- A Self-Evaluating Architecture for Describing Data -- Novel Hybrid Framework to Enhance Zero-shot Classification -- Attention-based Model for Accurate Stance Detection -- OPTICS: Automatic MT Evaluation based on Optimal Transport by Integration of Contextual Representations and Static Word Embeddings -- End-to-End Parkinson’s Disease Detection Using a Deep Convolutional Recurrent Network -- Lexical Bundle Variation in Business Actors’ Public Communications -- 50 Shades of Gray: Effect of the Color Scale for the Assessment of Speech Disorders -- Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets -- Detection of Prosodic Boundaries in Speech Using Wav2Vec 2.0 -- Text-to-Text Transfer Transformer Phrasing Model Using Enriched Text Input -- Lexicon-based vs. Lexicon-free ASR for Norwegian Parliament Speech Transcription -- On Comparison of Phonetic Representations for Czech Neural Speech Synthesis -- The Influence of Dataset Partitioning on Dysfluency Detection Systems -- Going Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments using Acoustic Features -- Dialogue Federated Learning in Heterogeneous Data Settings for Virtual Assistants –Corpus: A Multimodal Dataset for Smart Operating Room Speech Assistant using Interventional Radiology Workflow Analysis -- Investigating Paraphrasing-based Data Augmentation for Task-Oriented Dialogue Systems -- Transfer Learning of Transformers for Spoken Language Understanding -- Evaluation of Wav2Vec Speech Recognition for Speakers with Cognitive Disorders -- Fine-Tuning BERT for Generative Dialogue Domain Adaptation -- Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection -- Empathy and Persona of English vs. Arabic Chatbots: A Survey and Future Directions -- Going Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments using Acoustic Features -- Dialogue Federated Learning in Heterogeneous Data Settings for Virtual Assistants –Corpus: A Multimodal Dataset for Smart Operating Room Speech Assistant using Interventional Radiology Workflow Analysis -- Investigating Paraphrasing-based Data Augmentation for Task-Oriented Dialogue Systems -- Transfer Learning of Transformers for Spoken Language Understanding -- Evaluation of Wav2Vec Speech Recognition for Speakers with Cognitive Disorders -- Fine-Tuning BERT for Generative Dialogue Domain Adaptation -- Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection -- Empathy and Persona of English vs. Arabic Chatbots: A Survey and Future Directions.
Inhalt:
This book constitutes the proceedings of the 25th International Conference on Text, Speech, and Dialogue, TSD 2022, held in Brno, Czech Republic, in September 2022. The 43 papers presented in this volume were carefully reviewed and selected from 94 submissions. The topical sections "Text", "Speech", and "Dialogue" deal with the following issues: speech recognition; corpora and language resources; speech and spoken language generation; tagging, classification and parsing of text and speech; semantic processing of text and speech; integrating applications of text and speech processing; automatic dialogue systems; multimodal techniques and modelling.
Weitere Ausg.:
ISBN 9783031162695
Weitere Ausg.:
ISBN 9783031162718
Weitere Ausg.:
Erscheint auch als Druck-Ausgabe ISBN 9783031162695
Weitere Ausg.:
Erscheint auch als Druck-Ausgabe ISBN 9783031162718
Sprache:
Englisch
DOI:
10.1007/978-3-031-16270-1
Bookmarklink
