Information, action and negotiation in dialogue systems Staffan Larsson Kings College, Jan 2001.

Slides:



Advertisements
Similar presentations
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California USA
Advertisements

An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
Justification-based TMSs (JTMS) JTMS utilizes 3 types of nodes, where each node is associated with an assertion: 1.Premises. Their justifications (provided.
Negotiative dialogue some definitions and ideas. Negotiation vs. acceptance Clark’s ladder: –1. A attends to B’s utterance –2. A percieves B’s utterance.
Introduzione ai casi d’uso  Adriano Comai 1999 Pag. 1 Use Cases: an Introduction  Adriano Comai 1999.
Learning theories These theories see criminality as normal learned behavior. Some behavior is instinctive and is possessed by an individual at birth; the.
Dialogue types GSLT course on dialogue systems spring 2002 Staffan Larsson.
U1, Speech in the interface:2. Dialogue Management1 Module u1: Speech in the Interface 2: Dialogue Management Jacques Terken HG room 2:40 tel. (247) 5254.
Goteborg University Dialogue Systems Lab Introduction to dialogue systems Staffan Larsson Dialogsystem HT04.
Issues Under Negotiation Staffan Larsson Dept. of linguistics, Göteborg University SigDial, 15/
LE TRINDIKIT A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Spoken Dialogue Technology How can Jerry Springer contribute to Computer Science Research Projects?
A preliminary classification of dialogue genres or Correlating properties of activities with properties of dialogue systems Staffan Larsson Dept. of linguistics.
Goteborg University Dialogue Systems Lab WP1: GoDiS VCR application Edinburgh TALK meeting 7/
Research about dialogue and dialogue systems and the department of linguistics goal: –develop theories about human dialogue which can be used when building.
TrindiKit A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Issues Under Negotiation Staffan Larsson Dept. of linguistics, Göteborg University NoDaLiDa, May 2001.
01 -1 Lecture 01 Intelligent Agents TopicsTopics –Definition –Agent Model –Agent Technology –Agent Architecture.
Rough schedule Multimodal, multi-party dialogue [30 min] D’Homme, SIRIDUS [10 min] –dialogues with networked devices in a smart house SRI demo (DM), (IBL.
Goteborg University Dialogue Systems Lab GoDiS and TrindiKit MITRE workshop 27/10-03 Staffan Larsson Göteborg University Sweden.
Research Methods for HCI: Cognitive Modelling BCS HCI Tutorial 1 st September, 2008.
HFSD User Involvement Whilst the need to involve users in the SAD process is accepted to a greater or less extent in all design methods - the decision.
1 Training Counsellors for the Self-access Centre Pornapit Darasawang School of Liberal Arts King Mongkut’s University of Technology Thonburi
Publika, konzumace PhDr. Monika Metyková, PhD University of Sussex
INTRODUCTION TO ARTIFICIAL INTELLIGENCE Massimo Poesio Intelligent agents.
Computer Science 30/08/20151 Agent Communication BDI Communication CPSC /CPSC Rob Kremer Department of Computer Science University of Calgary.
22 November 2004 Multisession management in spoken dialogue system Hoá NGUYEN & Jean CAELEN.
Chapter 1 An overview of marketing Outline of the components of marketing practice and the text book.
PS429 Social and Public Communication PS429 Social and Public Communication Week 4 (25/10/2005) Reading group discussion.
Use Cases 2 ENGR ♯10 Peter Andreae
Cognitive Reasoning to Respond Affectively to the Student Patrícia A. Jaques Magda Bercht Rosa M. Vicari UNIVERSIDADE FEDERAL DO RIO GRANDE DO SUL BRASIL.
Theories of Discourse and Dialogue. Discourse Any set of connected sentences This set of sentences gives context to the discourse Some language phenomena.
Information, action and negotiation in dialogue systems Staffan Larsson Kings College, Jan 2001.
The Information State approach to dialogue modelling Staffan Larsson Dundee, Jan 2001.
Argumentation and Trust: Issues and New Challenges Jamal Bentahar Concordia University (Montreal, Canada) University of Namur, Belgium, June 26, 2007.
EEL 5937 Agent communication EEL 5937 Multi Agent Systems Lecture 10, Feb. 6, 2003 Lotzi Bölöni.
An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
From information exchange to negotiation Staffan Larsson Göteborg University
Interpretative Theories BASIC IDEAS The social world is a world made up of purposeful actors who acquire, share, and interpret a set of meanings, rules,
Sidner’s artificial negotiation language. Sidner: an artificial discourse language for collaborative negotiation Formal account of negotiative dialogue.
Issues in Multiparty Dialogues Ronak Patel. Current Trend  Only two-party case (a person and a Dialog system  Multi party (more than two persons Ex.
Towards a Theoretical Framework for the Integration of Dialogue Models into Human-Agent Interaction John R. Lee Assistive Intelligence Inc. Andrew B. Williams.
Intelligent Agents RMIT Prof. Lin Padgham (leader) Ass. Prof. Michael Winikoff Ass. Prof James Harland Dr Lawrence Cavedon Dr Sebastian Sardina.
Politeness & Speaking Style Discourse & Dialogue CS 359 November 15, 2001.
ERDA : An Empathic Rational Dialog Agent1 Magalie Ochs (1),(2), Catherine Pelachaud (1) and David Sadek (2) (1) IUT de Montreuil, University Paris VIII,
Information state and dialogue management in the TRINDI Dialogue Move Engine Toolkit, Larsson and Traum 2000 D&QA Reading Group, Feb 20 th 2007 Genevieve.
Information-State Dialogue Modelling in Several Versions HS Dialogmanagement, SS 2002 Universität Saarbrücken Michael Götze.
A Quantitative Trust Model for Negotiating Agents A Quantitative Trust Model for Negotiating Agents Jamal Bentahar, John Jules Ch. Meyer Concordia University.
Geoinformatics 2006 University of Texas at El Paso Evaluating BDI Agents to Integrate Resources Over Cyberinfrastructure Leonardo Salayandía The University.
Working with Conceptual Frameworks “We aren’t just making this all up.”
Computer Science CPSC /CPSC Rob Kremer Department of Computer Science University of Calgary 07/12/20151 Agent Communications.
Dialog Models September 18, 2003 Thomas Harris.
EEL 5937 Agent communication EEL 5937 Multi Agent Systems Lotzi Bölöni.
Negotiation Skills Mike Phillips Training Quality Manager
A preliminary classification of dialogue genres Staffan Larsson Internkonferens 2003.
AAAI Fall Symposium on Mixed-Initiative Problem-Solving Assistants 1 Mixed-Initiative Dialogue Systems for Collaborative Problem-Solving George Ferguson.
Goteborg University Dialogue Systems Lab Comments on ”A Framework for Dialogue Act Specification” 4th Workshop on Multimodal Semantic Representation January.
MERL 1 COLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction Charles Rich Candace L. Sidner Neal Lesh Mitsubishi Electric Research.
Intention & Cooperation Discourse and Dialogue CS 359 October 18, 2001.
Theories and Program Design
Intelligent Agents Chapter 2. How do you design an intelligent agent? Definition: An intelligent agent perceives its environment via sensors and acts.
Agent-Based Dialogue Management Discourse & Dialogue CMSC November 10, 2006.
Shared Intentionality
Learning theories These theories see criminality as normal learned behaviour. Some behaviour is instinctive and is possessed by an individual at birth;
Learning theories These theories see criminality as normal learned behaviour. Some behaviour is instinctive and is possessed by an individual at birth;
Understanding Behavior and Performance In Organizations
Intelligent Agents Chapter 2.
Teaching Java with the assistance of harvester and pedagogical agents
Learning theories These theories see criminality as normal learned behavior. Some behavior is instinctive and is possessed by an individual at birth; the.
Presentation transcript:

Information, action and negotiation in dialogue systems Staffan Larsson Kings College, Jan 2001

Overview dialogue modelling the information state approach & TrindiKit GoDiS – a dialogue system action- and information oriented dialogue negotiative dialogue

Dialogue modelling Theoretical motivations –find structure of dialogue –explain structure –relate dialogue structure to informational and intentional structure Practical motivations –build dialogue systems to enable natural human-computer interaction –speech-to-speech translation –...

Informal approaches to dialogue modelling speech act theory (Austin, Searle,...) –utterances are actions –illocutionary acts: ask, assert, instruct etc. discourse analysis (Schegloff, Sacks,...) –turn-taking, pre-sequences etc. dialogue games (Sinclair & Coulthard,...) –structure of dialogue segments (rather than separate utterances) –can e.g. be encoded as regular expressions or finite automata qna-game -> question qna-game* answer

Computational approaches implemented in systems and toolkits finite state automata (CLSU toolkit, Nuance) frame-based (Philips, SpeechWorks) plan-based (TRAINS, Allen, Cohen, Grosz, Sidner,...) general reasoning (Sadek,...) information states (TRINDI: Traum, Bos,...)

Inquiry- vs. action-oriented dialogue Inquiry oriented dialogue (IOD) has the primary goal of exchanging information –regardless of whether and how this information will be used in future actions Action oriented dialogue (AOD) has the primary goal of a participant performing or being obliged to perform an action (or plan, i.e. a complex action)

Inquiry-oriented dialogue utterance types: ask, answer Information-seeking dialogue: one DP asks the questions, the other answers them Information-exchange (information oriented) dialogue: both DPs ask questions and provide answers – can be seen as a sequence of infoseeking dialogues, possibly with embedded subdialogues

Action-oriented dialogue utterance types: request, confirm In simple AOD, only one participant becomes obliged/comitted to some action or plan Actions can either be performed ”online” while the dialogue is happening, or they may be stored as a plan to be performed after the dialogue (”offline”)

Negotiative dialogue utterance types: suggest, accept, reject What is it? –Negotiation is a type of problem-solving –Possible definition of negotiative dialogue: DPs discuss several alternative solutions to a problem before choosing one of them Negotiation does not imply conflicting goals –perhaps not 100% correspondence to everyday use of the word “negotiation”, but useful to keep collaborativity as a separate dimension from negotiation Both AOD and IOD can be negotiative –in a flight information service, the user does not become obliged to fly anywhere; so it’s IOD –but several different flights may be discussed

Negotiation tasks Some factors influencing negotiation –distribution of information between DPs (who knows what) –whether DPs must commit jointly (e.g. Coconut) or one DP can make the comittment (e.g. flight booking) We’re initially trying to model negotiation in flight booking –sample dialouge U: flights to paris on september 13 please S: there is one flight at 07:45 and one at 12:00 U: what airline is the 12:00 one S: the 12:00 flight is an SAS flight U: I’ll take the 12:00 flight please –Sys provides alternatives, User makes the choice –Sys knows timetable, User knows when he wants to travel etc.

Degrees of negotiativity non-negotiative dialogue: only one alternative is discussed semi-negotiative dialogue: a new alternative can be introduced by altering parameters of the previous alternative, but previous alternatives are not retained negotiative dialogue: several alternatives can be introduced, and old alternatives are retained and can be returned to

BDI: agents What is needed for intelligent behaviour? –perception –Beliefs –Desires –planning and decistion making ability (deliberation) –Intentions –ability to act To interact, also need social attitudes –common ground –obligations¨¨¨ –committments –rights

from AI: actions (e.g. buy a ticket) have –preconditions ( seller has ticket, buyer has money) –decomposition ( … ) –effects

BDI and speech acts ”normal” actions affect the external world speech acts affect mental states of agents –i.e. their beliefs, desires, intentions, … so, speech acts can be described in terms of preconditions and effects on mental states ConvinceByInform(S, H, P) [Allen] –roles: S=speaker, H=hearer, P=proposition –precondition: bel(S, P) –effect: bel(H, P)

later developments Traum –incorporate social attitudes –model the fact that utterances are not always successful initiate_assert(S, H, P) –precondition: int( S, mbel( S, H, P ) ) –effect: bel( H, int( S, mbel( S, H, P ) ) ) acknowledge_assert( S, H, P ) –precondition: bel( S, int( H, mbel( S, H, P ))) –effect: mbel( S, H, P )