Question Accommodation and Information States in Dialogue

Slides:



Advertisements
Similar presentations
Use Case Diagrams Damian Gordon.
Advertisements

An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
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.
MIS 325 PSCJ. 2  Business processes can be quite complex  Process model: any abstract representation of a process  Process-modeling tools provide a.
Presented by: Thabet Kacem Spring Outline Contributions Introduction Proposed Approach Related Work Reconception of ADLs XTEAM Tool Chain Discussion.
PHONEXIA Can I have it in writing?. Discuss and share your answers to the following questions: 1.When you have English lessons listening to spoken English,
Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004.
Dialogue types GSLT course on dialogue systems spring 2002 Staffan Larsson.
Dialogue Systems 2 GSLT Spring Purpose The purpose of the course is to –do real research on dialogue systems by –building on existing systems developed.
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.
VoiceXML vs. GoDiS/QPD. free order answering / question accommodation VXML: fields in a form may be filled in any order, given a form-level grammarform-level.
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.
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.
Information, action and negotiation in dialogue systems Staffan Larsson Kings College, Jan 2001.
1 Issue-based Dialogue Management Staffan Larsson 2003.
Modeling System Events Adapted from: Systems Analysis and Design in a Changing World, 2nd Edition by John W. Satzinger, Robert Jackson and Stephen Burd.
GoDiS (Gothenburg Dialogue System) with application to instructional text and dialogue ESSLLI, Helsinki 21st Aug 2001 Staffan Larsson
TrindiKit A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Grounding in dialogue systems Staffan Larsson Inst. för lingvistik, GU OFTI 2002, Göteborg.
Issues Under Negotiation Staffan Larsson Dept. of linguistics, Göteborg University NoDaLiDa, May 2001.
Menu2dialog Staffan Larsson, Robin Cooper, Stina Ericsson Department of linguistics Göteborgs Universitet.
LE A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach TrindiKit.
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.
WP1 UGOT demos 2nd year review Saarbrucken Mar 2006.
Sharif University of Technology Session # 7.  Contents  Systems Analysis and Design  Planning the approach  Asking questions and collecting data 
Mobile and Pervasive Computing - 8 Natural Language Processing Presented by: Dr. Adeel Akram University of Engineering and Technology, Taxila,Pakistan.
O BJECT O RIENTATION F UNDAMENTALS Prepared by: Gunjan Chhabra.
COMPUTER ASSISTED / AIDED LANGUAGE LEARNING (CALL) By: Sugeili Liliana Chan Santos.
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.
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
Database What is a database? A database is a collection of information that is typically organized so that it can easily be storing, managing and retrieving.
1 Introduction to Software Engineering Lecture 1.
Sharing Design Knowledge through the IMS Learning Design Specification Dawn Howard-Rose Kevin Harrigan David Bean University of Waterloo McGraw-Hill Ryerson.
Dept. of Computer Science University of Rochester Rochester, NY By: James F. Allen, Donna K. Byron, Myroslava Dzikovska George Ferguson, Lucian Galescu,
ENTERFACE 08 Project 1 “MultiParty Communication with a Tour Guide ECA” Mid-term presentation August 19th, 2008.
DenK and iCat Two Projects on Cooperative Electronic Assistants (CEA’s) Robbert-Jan Beun, Rogier van Eijk & Huub Prüst Department of Information and Computing.
Introduction to Dialogue Systems. User Input System Output ?
LECTURE 2: SEMANTICS IN LINGUISTICS
Introduction to Computational Linguistics
Model View Controller MVC Web Software Architecture.
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.
GoDiS AI-course, Chalmers April 22, 2002 Staffan Larsson.
Information-State Dialogue Modelling in Several Versions HS Dialogmanagement, SS 2002 Universität Saarbrücken Michael Götze.
Dialog Models September 18, 2003 Thomas Harris.
Intelligent Agents. 2 What is an Agent? The main point about agents is they are autonomous: capable of acting independently, exhibiting control over their.
Lti Shaping Spoken Input in User-Initiative Systems Stefanie Tomko and Roni Rosenfeld Language Technologies Institute School of Computer Science Carnegie.
A preliminary classification of dialogue genres Staffan Larsson Internkonferens 2003.
System Selection Dania Bilal IS 582 Spring System Selection Business Selection of system project to develop or enhance Libraries & other information.
Goteborg University Dialogue Systems Lab Comments on ”A Framework for Dialogue Act Specification” 4th Workshop on Multimodal Semantic Representation January.
User Responses to Prosodic Variation in Fragmentary Grounding Utterances in Dialog Gabriel Skantze, David House & Jens Edlund.
RADAR February 15, RADAR /Space-Time Learning.
Université Toulouse I 1 CADUI' June FUNDP Namur Implementation Techniques for Petri Net Based Specifications of Human-Computer Dialogues.
SELF-SERVE MOBILE O2 and Vodafone. SELF-SERVE The following requests can be completed in Self- Serve: Add Bolt On Remove Bolt On Amend Bolt On Tariff.
Agent-Based Dialogue Management Discourse & Dialogue CMSC November 10, 2006.
Survey Training Pack Session 3 – Questionnaire Design.
PRESUPPOSITION PRESENTED BY: SUHAEMI.
Wifi Based Menu Ordering By Samiksha Patil Shalini Yethendran Anitta Eaphen.
Predicting and Adapting to Poor Speech Recognition in a Spoken Dialogue System Diane J. Litman AT&T Labs -- Research
Human Computer Interaction Lecture 21 User Support
Development Environment
Agenda Preliminaries Motivation and Research questions Exploring GLL
Human Computer Interaction Lecture 21,22 User Support
Architecture Components
An Integrated Theory of the Mind
Contents Introduction Motivation Objectives
Presentation transcript:

Question Accommodation and Information States in Dialogue Staffan Larsson, Robin Cooper, Elisabet Engdahl Department of linguistics Göteborg University, Sweden

Structure of this talk Key concepts Introduction to the GoDIS system Information-seeking dialogue Question accommodation Task accommodation Focus and information states

The information state approach – key concepts Information states represent information available to dialogue participants, at any given stage of the dialogue Dialogue moves trigger information state updates, formalised as information state update rules TrindiKit: software package for implementing dialogue systems; based on the information state approach to dialogue management (->David Traum)

GoDiS: a dialogue system Implemented using the TrindiKit Information-seeking dialogue Information state based Ginzburg’s notion of Questions Under Discussion (QUD) a stack (or partially ordered set) of questions which have been raised and can be answered elliptically Dialogue plans to drive dialogue QUD and dialogue plans provide the right level of complexity for information-seeking dialogue Simple “optimistic” grounding strategy Question and task accommodation Focus intonation based on information state contents (partially implemented)

GoDiS & TrindiKit TrindiKit domain-specific GoDiS system domain & language resources QUD-based dialogue theory (IS, rules, ...) generic GoDiS system TrindiKit information state approach

GoDiS features (cont’d) Adapted for travel agency and autoroute domains (also being adapted to cinema booking, and to function as dialogue interface to a handheld computer and a mobile phone) Lexicons for English and Swedish; lexicon can be switched dynamically

control input inter- pret update select gene- rate output Information State lexicon data- base domain

Sample GoDiS information state AGENDA = { findout(?return) } findout(?x.month(x)) findout(?x.class(x)) respond(?x.price(x)) PRIVATE = PLAN = BEL = { } TMP = ( same as SHARED ) dest-city(paris) transport(plane) task(get_price_info) BEL = SHARED = QUD = < x.origin(x) > LM = { ask(sys, x.from-city(x)) }

Sample GoDiS update rule integrateAnswer Before an answer can be integrated by the system, it must be matched to a question on QUD in(SHARED.LM, answer(usr, A)) fst(SHARED.QUD, Q) relevant_answer(Q, A) pre: pop(SHARED.QUD) apply(Q, A, P) add(SHARED.COM, P) eff:

Information-seeking dialogue User needs to give information which enables the system to perform its task (booking a ticket, providing price information etc.) Typical dialogue system behaviour: user must give information in the order determined by the system questions

Typical human-computer dialog S: Hello, how can I help you? U: I want price information please S: Where do you want to go? U: Paris S: How do you want to travel? U: A flight please S: When do you want to travel U: April S: what class did you have in mind? … S: The price is $123

Dialogue plans for information-seeking dialogue Find out how user wants to travel Find out where user wants to go to Find out where user wants to travel from Find out when user wants to travel … Lookup database Tell user the price

Typical human-human dialogue S(alesman), C(ustomer) S: hi C: flights to paris S: when do you want to travel? C: april, as cheap as possible ...

Accommodation Lewis (1979): If someone says something at t which requires X to be in the conversational scoreboard, and X is not in the scoreboard at t, then (under certain conditions) X will become part of the scoreboard at t Has been applied to referents and propositions, as parts of the conversational scoreboard / information state

Question accommodation If questions are part of the information state, they too can be accommodated If the latest move was an answer, and there is an action in the plan to ask a matching question, put that question on QUD Requires that the number of possible matching questions is not too large (or can be narrowed down by asking clarification question)

Update rule for question accommodation QuAcc in(SHARED.LM, answer(usr, A)) in(PRIVATE.PLAN, findout(Q)) relevant_answer(Q, A) pre: delete(PRIVATE.PLAN, findout(Q)) push(SHARED.QUD, Q) eff:

Task accommodation In some cases, the system may not even know what task the user wants the system to perform If latest move was an answer, and there is currently no plan, find (in the domain resource) a task and corresponding plan containing a matching question; accommodate the task and load the appropriate plan Similar to plan recognition, but no dynamic plan reconstruction or assumption that the full plan is shared

Update rule for task accommodation - An answer move matches a task if the plan contains a question matching the answer - More complex version generates clarification question if the number of plans > 1 in(SHARED.LM, Move) domain :: match_task(Move, Task, Plan) pre: add(SHARED.BEL, task(Task)) set(PRIVATE.PLAN, Plan) eff:

Question and task accommodation in information-seeking dialogue S: hi U: flights to paris system finds plan containing appropriate questions, and loads it into the plan field in the information state system accommodates questions: how does user want to travel + where does user want to go, and integrates the answers “flight” and “to paris” system proceeds to next question on plan S: when do you want to travel?

Why accommodation? Generality no need to distinguish requested and non-requested (but relevant) information single rule for integrating answers Theoretically motivated concept, with independent justification Easy to implement, given information state approach

Extensions Questions can also be reaccommodated if the user answers a question which has already been answered: remove proposition from shared beliefs, and put question back on QUD Extend to domain where there are many plans containing a question matching a given answer e.g. menu-based dialogue Focus intonation and QUD

Focus and information states Focal Question Presupposition (FQP) (based on Ginzburg and others): An utterance with narrow focus on a constituent presupposes a function/question obtained by abstracting over the focussed constituent Example: “Jill likes BILL” [like(jill, bill)] presupposes “Who does Jill like?” [?lx.like(jill, x)]

Focal Question Accommodation FQuAcc: interpretation version of FQP “When an utterance occurs which focally presupposes Q, and Q is not topmost on QUD, make Q topmost on QUD” in(SHARED.LM, Move) foc-presupp(Move, Q) ~fst(SHARED.QUD , Q) pre: push(SHARED.QUD, Q) eff:

Interpreting utterances with focus Example: A: Are you FLYING to london? Q = ?(to-city(london)&transport(fly)) presupposes Q’ = ?(lx.to-city(london)&transport(x)), i.e. “how are you getting to london” B1: Yes B2: No, I’m taking a TRAIN ?B3: No [Q’ still on QUD!]

Generating utterances with focus Generation version of FQP: When generating Q, and there is a Q’ on QUD such that Q’ is an abstraction of Q over constituent C (Q=Q’(C)), put narrow focus on C

Generating utterances with focus (cont’d) Example 1: U: I want a flight please S: Where city do you want to go to? (Q’) U: London S: So you’re flying to LONDON? (Q) [Q=Q’(london); Q’ still on QUD, so put focus on “London”] Example 2: U: I want to go to London S: How do you want to travel? (Q’) U: A flight please S: So you’re FLYING to London? (Q)

Conclusion Question and task accommodation support natural interactive dialogue, where user controls in which order information is presented Information state approach enables easy implementation of question and task accommodation Implemented in GoDiS using the TRINDIKIT software package (www.ling.gu.se/research/projects/trindi/trindikit.html) Focus can be generated and interpreted using information state, esp. QUD

Want more? Menu-based dialogue generating focus based on Global QUD Clarification questions

Menus vs. dialogue Menu-driven interaction is ubiquitous: automated cinema ticket booking, mobile phones, computers, video recorders… Often tedious and frustrating; hard to find what you want; inflexible Can be straightforwardly implemented as dialogue systems, but you still have to descend the menu structure one node at a time

Typical menu-based dialogue S: What do you want to do? U: Search the phonebook S: What name do you want to search for? U: John S: John’s number is 0312345566. Do you want to call John? U: Yes S: Calling John.

Plans derived from menu structure Toplevel: ask what user wants to do (phonebook, messages etc); load corresponding plan Phonebook: ask what user wants to do (search phonebook, add to phonebook etc); load corresponding plan Search phonebook: ask for name; if name exists, inform of number; ask if user wants to call number; if yes, call number

Question and task accommodation in menu-based dialogue U: John system finds several plans containing a request for a name, and asks the user which one is correct S: Do you want to search the phonebook for John? U: Yes, and call him up system accommodates answer to the question whether user wants to call S: John’s number is 0312345566. Calling John.

Strategies for asking clarification questions Ask a series of yes/no-questions, one for each alternative; OK if user can interrupt Ask wh-question; if user does not provide answer, list alternatives Ask alternative question

Global QUD The QUD in GoDiS is very local GoDiS could be extended with a global QUD, containing all questions which have been asked so far This would enable e.g. reraising of questions (See Cooper et. al., Gotalog 2000) Also, a global QUD could be used in generation of questions with focus intonation

Generating questions with focus II If a question Q1 is to be asked, and there is a parallel question Q2 in GQUD, put focus on the part that differentiates Q1 and Q2 lx.to-city(x) parallell to lx.from-city(x) Example: S: What CITY do you want to go to? U: Paris .... S: What city do you want to go FROM?

Generating questions with focus II (cont’d) Extension to focal question presupposition: A question Q with narrow focus on C presupposes a parallell question Q’’ which differs from Q by having C replaced by some B Does accommodation apply? What about propositions? What, exactly, does “parallell” mean? (cf. Pulman 1998 for a formal account of parallellism for propositions)