Record:   Prev Next
作者 Lison, Pierre
書名 Robust Processing of Spoken Situated Dialogue : A Study in Human-Robot Interaction
出版項 Hamburg : Diplomica Verlag, 2010
©2010
國際標準書號 9783836641135 (electronic bk.)
9783836691130
book jacket
版本 1st ed
說明 1 online resource (198 pages)
text txt rdacontent
computer c rdamedia
online resource cr rdacarrier
附註 Robust Processing of Spoken Situated Dialogue -- Abstract -- Zusammenfassung -- Résumé -- Acknowledgements -- Introduction -- Processing spoken dialogue -- The issues -- Key ideas of our approach -- Discussion and relation to previous work -- Human-robot interaction -- A short historical background -- Scientific relevance of HRI -- Dimensions of HRI -- Cognitive systems for HRI -- Considered scenarios -- Playmate scenario -- Explorer scenario -- Outline -- Contributions -- I Background -- Situated spoken dialogue -- Linguistic analysis of spoken dialogue -- Example from the Apollo corpus -- Theoretical analysis -- Language, context and human cognition -- Phylogenetic and ontogenetic origins -- Situated human language processing -- Five working hypotheses -- Summary of the chapter -- Theoretical foundations -- Combinatory Categorial Grammar -- Lexicon -- Combinatory rules -- Derivations -- Hybrid Logic Dependency Semantics -- Hybrid logic -- Encoding linguistic meaning -- Syntax-semantics interface -- Segmented Discourse Representation Theory -- Dynamic semantics -- Rhetorical relations -- The SDRT approach in brief -- Event structure -- Summary of the chapter -- Software architecture -- Global architecture -- Cognitive Systems Architecture Schema -- CAST: an implementation toolkit for CAS -- The communication subarchitecture -- Representations -- Processes -- Summary of the chapter -- II Approach -- Situated Speech Recognition -- Introduction to the issue -- Psycholinguistic motivation -- Salience modeling -- Visual salience -- Linguistic salience -- Cross-modal salience model -- Lexical activation -- Language modeling -- Corpus generation -- Salience-driven, class-based language models -- Evaluation -- Evaluation procedure -- Results -- Analysis -- Summary of the chapter -- Robust Parsing of Spoken Dialogue -- Grammar relaxation
New type-shifting rules -- Paradigmatic heap rules -- Discourse-level composition rules -- ASR error correction rules -- Control of grammar relaxation -- Discriminative models for parse selection -- Definition of the task -- A distribution-free approach -- Learning -- Training data -- Averaged perceptron -- Decoding -- Features -- Semantic features -- Syntactic features -- Contextual features -- Speech recognition features -- Additional extensions -- Incremental parse selection -- Max-margin classifier (SVM) -- Summary of the chapter -- III Evaluation & Conclusion -- Evaluation -- Testing data -- Evaluation procedure -- Types of quantitative results -- Quantitative results -- Comparison with baseline -- Discussion of results -- Conclusion -- Suggestions for further research -- IV Appendices -- Packing algorithm -- Example -- Data structures -- Pseudo-code -- Detailed results for parse selection -- Tables -- Figures -- Global results with all NBest hypotheses -- Detailed results for exact-match -- Detailed results for partial-match -- Domain-specific grammar for corpus generation -- Definitions -- Grammar specification -- References -- Index
Recent years have witnessed a surge of interest for service robots endowed with communicative abilities. Such robots could take care of routine tasks, in homes, offices, schools or hospitals, help disabled or mentally impaired persons, serve as social companions for the elderly, or simply entertain us. They would assist us in our daily life activities. These robots are, by definition, meant to be deployed in social environments, and their capacity to interact naturally with humans is thus a crucial factor. The development of such "talking robots" led to the emergence of a new research field, Human-Robot Interaction (HRI), which draws from a wide range of scientific disciplines such as artificial intelligence, robotics, linguistics and cognitive science. This work focuses on the issue of robust speech understanding - that is, how to process spoken dialogue automatically to extract the intended meaning. The book presents a new approach which combines linguistic resources with statistical techniques and context-sensitive interpretation to achieve both deep and robust spoken dialogue comprehension. The first part of the book provides a general introduction to the field of human-robot interaction and details the major linguistic properties of spoken dialogue, as well as some grammatical formalisms used to analyse them. The second part describes the approach itself, devoting one chapter to context-sensitive speech recognition for HRI, and one chapter to the robust parsing of spoken inputs via grammar relaxation and statistical parse selection. All the algorithms presented are fully implemented, and integrated as part of a distributed cognitive architecture for autonomous robots. A complete evaluation of our approach using Wizard-of-Oz experiments is also provided in this book. The results demonstrate very significant improvements in accuracy and
robustness compared to the baseline
Description based on publisher supplied metadata and other sources
Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2020. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries
鏈接 Print version: Lison, Pierre Robust Processing of Spoken Situated Dialogue : A Study in Human-Robot Interaction Hamburg : Diplomica Verlag,c2010 9783836691130
主題 Natural language processing (Computer science);Automatic speech recognition
Electronic books
Record:   Prev Next