TAILIEUCHUNG - Báo cáo khoa học: "Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems"

We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (. a user and a surface realiser). We study its use in a standard NLG problem: how to present information (in this case a set of search results) to users, given the complex tradeoffs between utterance length, amount of information conveyed, and cognitive load. We set these trade-offs by analysing existing MATCH data. We then train a NLG policy using Reinforcement Learning (RL), which adapts its behaviour to noisy feedback from. | Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems Verena Rieser School of Informatics University of Edinburgh vrieser@ Oliver Lemon School of Informatics University of Edinburgh olemon@ Abstract We present and evaluate a new model for Natural Language Generation NLG in Spoken Dialogue Systems based on statistical planning given noisy feedback from the current generation context . a user and a surface realiser . We study its use in a standard NLG problem how to present information in this case a set of search results to users given the complex tradeoffs between utterance length amount of information conveyed and cognitive load. We set these trade-offs by analysing existing MATCH data. We then train a NLG policy using Reinforcement Learning RL which adapts its behaviour to noisy feedback from the current generation context. This policy is compared to several baselines derived from previous work in this area. The learned policy significantly outperforms all the prior approaches. 1 Introduction Natural language allows us to achieve the same communicative goal what to say using many different expressions how to say it . In a Spoken Dialogue System SDS an abstract communicative goal CG can be generated in many different ways. For example the CG to present database results to the user can be realized as a summary Polifroni and Walker 2008 Demberg and Moore 2006 or by comparing items Walker et al. 2004 or by picking one item and recommending it to the user Young et al. 2007 . Previous work has shown that it is useful to adapt the generated output to certain features of the dialogue context for example user preferences . Walker et al. 2004 Demberg and Moore 2006 user knowledge . Janarthanam and Lemon 2008 or predicted TTS quality . Nakatsu and White 2006 . In extending this previous work we treat NLG as a statistical sequential planning problem analogously to current statistical approaches to Dialogue .

• Báo cáo khoa học
• Natural Language Generation
• Planning Under Uncertainty
• Spoken Dialogue Systems
• scientific reports
• model language
• process natural language
• THE TEXT SYSTEM
• Kathleen R
• M
• MENTING A DATABASE
• KNOWLEDGE REPRESENTATION
• THE KEY TO THE SELECTION PROBLEM
• E
• Jeffrey Conklin David D
• McDonald
• NAtural Language driven
• Image Generation
• Giovanni Adorni
• Mauro Di Manzo and Fausto Giunchiglis
• A MODEL OF REVISION
• Marie M
• Vaughan David D
• Applying Explanation based
• Learning to Control
• Speeding up Natural Language Generation
• Integrating Natural
• Language Generation
• XML Web Technology
• NATURAL LANGUAGE INPUT
• SCENE GENERATION
• A Computational Theory of ProseStyle
• David D
• PROBLEM SOLVING APPLIED
• Long Papers
• AN APPLICATION OF AUTOfIATED LANGUAGE
• UNDERSTANDI;IG TECHNIQUES TO THE GENERATION
• DATA BASE ELEMENTS
• DEALING WITH INCOMPLETENESS
• LINGUISTIC KNOWLEDGE IN LANGUAGE TRANSLATION TRANSFER AND GENERATION STAGE
• MU MACHINE TRANSLATION PROJECT
• LANGUAGE SYNTHESIS GENERATION OF GERMAN
• CONCEPTUAL STRUCTURE
• MT PROJECT IN A JAPANESE GERMAN
• TWO TYPES OF PLANNING
• Eduard H
• Hovy
• Lexical Selection
• the Process of Language Generation
• AUTOMATICALLY EXTRACTING
• REPRESENTING COLLOCATIONS
• A comparison of clausal coordinate ellipsis in Estonian
• German Remarkably similar elision rules allow a language independent
• ellipsis generation module
• Lexical Choice Criteria
• Manfred Stede
• TENSE GENERATION IN AN INTELLIGENT TUTOR
• FOREIGN LANGUAGE TEACHING
• SOME ISSUES IN THE DESIGN OF THE VERB EXPERT
• DESIGNING ILLUSTRATED TEXTS
• HOW LANGUAGE PRODUCTION IS INFLUENCED
• GRAPHICS GENERATION
• Automated planning
• situated natural language generation
• Konstantina Garoufi and Alexander Koller
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• A Flexible
• Disabled Children
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Towards Web Based
• Evaluation of Automatic Natural Language
• Phrase Generation
• Instance based Sentence Boundary
• Determination by Optimization