Transcript
Page 1: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

1

Gu Dialogue Systems Lab

Issue-based Dialogue Management in GoDiS

Staffan LarssonDialogsystem

HT 2004

Page 2: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

2

Gu Dialogue Systems Lab

Overview

1. Goals2. Basic issue-based dialogue

management3. Grounding and feedback4. Adressing Unraised Issues5. Action-oriented Dialogue6. Multilinguality7. Conclusions

Page 3: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

3

Gu Dialogue Systems Lab

1. Goals

• Explore and implement issue-based dialogue management– starting from a theory of dialogue semantics (by Jonathan

Ginzburg) – based on notions of

• DGB (Dialogue Gameboard) • QUD (Questions Under Discussion)• Update Protocols

– adapt this theory to dialogue system (GoDiS) and implement it using TrindiKit

– extend theory coverage, taking in relevant theories

• General theory of dialogue– minimize effort for adapting dialogue system to new

domains

Page 4: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

4

Gu Dialogue Systems Lab

Goals cont’d

• Incrementally extend theory and system to handle increasingly complex types of dialogue– clarifies relation between dialogue genres– promotes reuse of update rules

• Some dialogue phenomena covered– Multiple tasks, information sharing between tasks – Feedback and grounding– Accommodation, re-raising, clarification– Menu based action oriented dialogue– Multi-linguality & multiple domains

Page 5: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

5

Gu Dialogue Systems Lab

• information state– an abstract data structure (record, DRS, set, stack etc.)– accessed by modules using conditions and updates

• dialogue moves are associated with IS updates using IS update rules– rule name and class– preconditon list: conditions on TIS– effect list: updates on TIS

• dialogue move engine– module or group of modules responsible for – updating the IS based on observed moves– selecting moves to be performed

Information State Approach

Page 6: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

6

Gu Dialogue Systems Lab

inputinter-pret

TIS

DATABASE LEXICON DOMAIN

data-base

control

update selectgene-rate

output

lexicon domainknowledge

DME

Page 7: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

7

Gu Dialogue Systems Lab

TrindiKit

GoDiS

GoDiS-I GoDiS-A

TravelAgency

Auto-route

Xeroxmanual

VCRmanager

IBDM

homedevice

manager

ISapproach

genre-specific

application-specific

Page 8: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

8

Gu Dialogue Systems Lab

2. Issue-based dialogue management

• Inquiry-oriented dialogue (database search)• basis:

– Ginzburg’s Dialogue Gameboard (DGB) and – related DGB update protocols

• dialogue moves: ask, answer, greet, quit• raising and addressing issues

– incl. short answers. e.g.”yes”, ”no”, ”paris”, ”in april”

• dialogue plans• sample domain: travel agency• extension:

– reraising issues– handling multiple issues

Page 9: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

9

Gu Dialogue Systems Lab

Semantics

• Simple First Order Logic without quantifiers, but with questions

• Questions– Y/N-questions: ?P, P is a proposition– wh-questions: ?x.p(x) (p is a predicate)

• ? works much like like – alt-questions: {?P1, …, ?Pn}

• Content of short answers– individual markers: paris, april, …– yes, no

Page 10: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

10

Gu Dialogue Systems Lab

Semantics, cont’d

• Q-A relations (adapted from Ginzburg)– resolves(A,Q): A resolves Q

• dest-city(paris) resolves ?x.dest-city(x)

– relevant(A,Q): A is relevant to Q (about Q)• not(dest-city(paris)) is relevant to ?

x.dest-city(x), but does not resolve it

Page 11: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

11

Gu Dialogue Systems Lab

Basic GoDiS information state record type

• QUD: Questions which have been raised but not resolved, and which are available for resolution of short answers

PRIVATE :PLAN : stackset( Action )

AGENDA : stack( Action )

SHARED :

BEL : set( Prop )

COM : set( Prop )

QUD : stackset( Question )

LU: SPEAKER: Speaker MOVES: OpenQueue( Move )

Page 12: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

12

Gu Dialogue Systems Lab

Sample dialogue plan

<findout(?x.dest-city(x))findout(?x.depart-city(x))findout(?x.transport(x))findout(?x.dept-month(x))findout(?x.dept-day(x))raise({?class(economy), ?class(business)}

consultDB(?x.price(x)) >

Page 13: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

13

Gu Dialogue Systems Lab

Answer integration

RULE: integrateAnswerPRE: in( $/SHARED/LU/MOVES, answer(A) )

fst( $/SHARED/QUD, Q )$DOMAIN :: relevant( A, Q )

EFF: ! $DOMAIN: combine( Q, A, P )add( /SHARED/COM, P )

• Before an answer can be integrated by the system, it must be matched to a question on QUD

Page 14: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

14

Gu Dialogue Systems Lab

Basic dialogue with updates

U: ”price information please”; raises price issue– if user asks Q, push Q on QUD and push respond(Q) on

AGENDA– if respond(Q) on AGENDA and PLAN empty, find plan for Q

and load to PLAN– if findout(Q) first on PLAN, ask Q

S: ”where do you want to go?”U: ”Paris”

– if LU/MOVES contains answer(A) and A relevant to Q, add P=Q[A] to SHARED.COM

– if P in SHARED.COM and Q topmost on QUD and P resolves Q, pop QUD

– if P in SHARED.COM and P resolves Q and findout(Q) on PLAN, pop PLAN

Page 15: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

15

Gu Dialogue Systems Lab

Basics cont’d

• …S: ”Do you want economy class or

business class?”U: ”economy class”

– if consultDB(Q) on PLAN, consult database for answer to Q; store result in PRIVATE.BEL

– if Q on QUD and P in PRIVATE.BEL s.t. P resolves Q, answer(P)

S: ”The price is £123”

Page 16: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

16

Gu Dialogue Systems Lab

Information sharing across plans

• GoDiS does not keep track of when propositions were added, or which plan was being executed

• so information sharing is determined by question sharing across plans

• plan for VISA question:findout(?x.dest-city(x))findout(?x.citizenship(x))– shares a questions with plan for ?x.price(x)

• so if visa-issue raised after price-issue, no need to ask for destination again

Page 17: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

17

Gu Dialogue Systems Lab

Dealing with multiple open issues

• if user asks Q, push Q on QUD and load plan for dealing with Q

• if users asks Q’ while system is dealing with Q, throw out plan for Q but Q remains on QUD; load plan for Q’

• when Q’ resolved, Q topmost on QUD will trigger reloading plan for dealing with Q– general rule: if SHARED.COM contains info resolving

Q, don’t ask Q– so any resolved questions in plan will be thrown out

Page 18: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

18

Gu Dialogue Systems Lab

Sample dialogue: multiple tasks & info sharing

S> Welcome to the travel agency! U> price information S> (…) Lets see. How do you want to travel? U> by flightS> (…) What city do you want to go to? U> parisS> (…) What city do you want to go from? U> do I need a visa ?S> (…) Lets see. What country are you from? U> swedenS> Okay. Yes, you need a Visa. S> Returning to the issue of price. Lets see. What city do

you want to go from?

Page 19: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

19

Gu Dialogue Systems Lab

A problem with QUDA: Who won the world cup?B: Where?A: in ItalyB: Are you sure it wasn’t in France?A: YesB: Where did you say it was again?A: ItalyB: Germany

• If QUD=<q1,q2> and q1 is resolved, q2 is available for resolution of short answers– takes no account of how many turns since q2 was raised– but short answers a long distance away from the question are

not as easily processed as an adjacent answer

Page 20: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

20

Gu Dialogue Systems Lab

ISSUES and QUD

• We extend Ginzburg’s DGB by adding ISSUES of type Stack(Question)

• ISSUES contains all raised but unresolved questions – ISSUES determines relevance of user answers

• QUD used for resolving short answers– questions drop off QUD after N turns– a short answer to a question that’s on ISSUES

but not QUD requires adjusting QUD by copying a question on ISSUES

Page 21: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

21

Gu Dialogue Systems Lab

3. Grounding and feedback

• ICM– Interactive Communication Management

• Grounding– making sure that the participants are percieving,

understanding, and accepting each other’s utterances– dealing with problematic situtations where e.g. an

utterance is not percieved• Feedback moves

– (short) utterances which signal grounding status of previous utterance

• Sequencing moves– utterances which signal switching task (”returning to…”),

reraising questions (”so…”) etc.

Page 22: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

22

Gu Dialogue Systems Lab

Grounding moves

• We want a typology of feedback moves• Some parameters:

– Action levels in dialogue (Allwood, Clark) • contact (con)• perception (per)• understanding

– Word meanings (sem)– Contextual meaning (und)

• acceptance (acc)– Polarity

• Positive (pos)• Negative (neg)• Checking (chk / int)

Page 23: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

23

Gu Dialogue Systems Lab

Some grounding moves in GoDiS• Formal representation

– icm:Level/Type{*Polarity}{:Content}

• Feedback moves– icm:und*neg – ”I don’t understand”– icm:und*pos:P – ”To Paris.”– icm:acc*neg:Q – ”Sorry, I can’t …”– icm:acc*pos – ”Okay”

• Feedback type selected depending on– Quality of recognised speech– Whether system can find a (relevant) interpretation– Whether system can accept what’s been said

• Sequencing moves– icm:reraise:Q – ”Returning to the issue of Q”– icm:loadplan – ”Let’s see…”

Page 24: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

24

Gu Dialogue Systems Lab

Grounding on multiple levels

S> Lets see. What can I do for you? U> (mumble mumble)S> Sorry, I didnt hear what you said. What can I do for you?

U> siridusS> I heard you say siridus . Sorry, I dont understand. What can Ido for you?

U> channel oneS> channel one. I dont quite understand. Do you want to add aprogram or change channel?

(dialog3a_edit)

Negative perception

feeback

Positive perception

Negative understanding

(sem)

Positive understanding

(word meaning)

Negative understanding

(und) Task clarification

Page 25: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

25

Gu Dialogue Systems Lab

U> turn on the t vS> turn on the TV… Sorry, I cannot control the TV set. Do you want to

add a program or change channel?”

U> pardonS> Sorry, I cannot control the TV set. Do you want to add a program or

change channel?U> change channelS> Okay.

(dialog3b_edit)

Rejection(negative

acceptance feedback)

Positiveunderstanding

User negative perception

System repetition

Positiveacceptance

Page 26: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

26

Gu Dialogue Systems Lab

Correcting the system

S> Lets see. What can I do for you? U> add programS> Okay. Add a program…S> Lets see. What channel do you want? U> channel sixS> okay, channel five.U> noS> not channel five. So, What channel do you want? U> channel sixS> channel six?”

(dialog4_edit)

Positive feedback

Negative answer to fb.

Signals reraising (Sequencing ICM)

Page 27: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

27

Gu Dialogue Systems Lab

4: Addressing Unraised Issues

• (QUD and ISSUES)• General strategy: question

accommodation• issue accommodation • QUD accommodation• dependent issue accommodation• issue reacommodation

Page 28: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

28

Gu Dialogue Systems Lab

Typical human-human dialogue

S(alesman), C(ustomer)S: hiC: flights to parisS: when do you want to travel?C: april, as cheap as possible...

Page 29: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

29

Gu Dialogue Systems Lab

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

Page 30: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

30

Gu Dialogue Systems Lab

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, then– put that question on ISSUES – (and QUD if it is a short answer)

• Requires that the number of possible matching questions is not too large – (or can be narrowed down by asking

clarification question)

Page 31: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

31

Gu Dialogue Systems Lab

issue accommodation PLANISSUES

• If – LM=answer(A) – no Q in ISSUES s.t. relevant(A,Q)

• then– find findout(Q) in PLAN s.t. relevant(A,Q)– push Q on ISSUES

• used when prevously unraised question (available in plan) is answered using a short or full answer

Page 32: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

32

Gu Dialogue Systems Lab

QUD accommodation ISSUESQUD

• If – LM=answer(A)– A is a short answer– no Q in QUD s.t. relevant(A,Q)

• then– find Q in ISSUES s.t. relevant(A,Q)– push Q on QUD– raise Q in ISSUES (make Q topmost)

• used when– previously raised question has dropped off QUD, but is

answered using a short answer– previously unraised question is answered using short

answer [needs PLANISSUES accommodation]

Page 33: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

33

Gu Dialogue Systems Lab

dependent issue accommodationDOMAINISSUES (+PLAN)

• If – LM=answer(A)– no Q in ISSUES s.t. relevant(A,Q)– no findout(Q) in PLAN s.t. relevant(A,Q)

• then– find Plan for some Q’ in DOMAIN s.t. findout(Q) or

raise(Q) in Plan and relevant(A, Q)– push Q’ on ISSUES– set PLAN to Plan

• used when previously unraised question, unavailable in PLAN, is answered using full or short answer (AKA ”task accomodation”)

Page 34: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

34

Gu Dialogue Systems LabSample dialogue:

accommodationS: Welcome to the travel agency.U: From London to Paris in April

– not relevant to any question that has been raised, or to any current plan

– look in domain knowledge for a plan (for dealing with some question Q) with matching questions

– load this plan, push Q on ISSUES– find in the plan the question(s) matching the user’s answer, and push

them onto ISSUES– integrate answer (requres matching question on ISSUES)

S: Alright, you want to know about price. (…)

– proceed to next plan item

S: How do you want to travel?– ISSUES=<?x.how(x), ?x.price(x)>

Page 35: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

35

Gu Dialogue Systems Lab

Task clarification (VCR application)

S> What can I do for you? U> channel fiveS> channel five. I dont quite understand. Do you

want to add a program or change channel?U> change channelS> Okay. change channel.S> Lets see. channel five?U> yesS> The channel was changed

Page 36: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

37

Gu Dialogue Systems Lab

Issue reaccommodation SHARED.COMISSUES

• If – LM=answer(A) – no Q in ISSUES s.t. relevant(A,Q)– P in SHARED.COM s.t. there is a Q s.t.

relevant(A,Q) and relevant(P,Q)

• then– push Q on ISSUES– remove P from SHARED.COM

• Used when previously resolved question is answered again

Page 37: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

38

Gu Dialogue Systems Lab

Revision by reaccommodation and reraising

S> What can I do for you? U> add program channel fiveS> Okay. Do you want to add a program?U> yesS> Lets see. channel five?U> yesS> What date? U> channel sixS> Okay. channel six… What date?

Page 38: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

39

Gu Dialogue Systems Lab

5: Issues and goals in Action-Oriented Dialogue (AOD)

• each goal action associated with a dialogue plan

• add field– SHARED.ACTIONS : StackSet(Action)

• New moves: request(Action), report(Action, Status)

• ACTIONS has a similar role to ISSUES• adapt accommodation strategies to

AOD

Page 39: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

40

Gu Dialogue Systems Lab

AOD information state

PRIVATE :PLAN : stackset( Action )

AGENDA : stack( Action )

SHARED :

BEL : set( Prop )

TMP : (same type as SHARED)

COM : set( Prop )

QUD : stackset( Question )

ACTIONS : stackset( Action )

LU:…

ISSUES: stackset(Question)

Page 40: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

41

Gu Dialogue Systems Lab

Requests vs. answers

• requests adresses a general question– ”what shall I do next?”, ”what can I do for you?” or

similar (”prompt”)– semantics in AOD: ?x.action(x)

• dialogue– ”What can I do for you?” raises?x.action(x) – ”Search the phonebook” interpreted as

request(search_phonebook)

• Rule: – If ?x.action(x) is topmost on ISSUES and L-M is

request(a)– then pop ISSUES

Page 41: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

42

Gu Dialogue Systems Lab

Action Oriented Dialogue subtypes

• ”Command dialogue”– user instructs system to perform actions

• device control; menu-based• travel agency booking

• ”Instructional dialogue”– system instructs user to perform actions

• ”interactive manual”

– system can explaing how to perform some action

• joint planning– user and system jointly agree to a plan– also involves negotiation

Page 42: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

43

Gu Dialogue Systems Lab

input

nuanceinter-pret

Information StateLEXICON DOMAIN DEVICES

lexiconvcrphone

control

update select gene-rate

outputnuance

devicephone

domainvcrphone

devicevcr

lexiconhome

domainhome

rel1

rel2

dim10

VCR

devicealert

Page 43: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

44

Gu Dialogue Systems LabConverting menus to plans

Menu Planmulti-choice list P1, P2, ..., Pn

findout({?P1,?P2,...,?Pn})

tick-box +/-P findout(?P)

dialogue windowp=___

findout(?x.p(x))

pop-up message M

answer(M)

Page 44: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

45

Gu Dialogue Systems Lab

Menu-based AODS: Welcome to the telephone and VCR manager!U: Channel one todayS: Right, I assume you want to add a program. Let’s see. Okay.

Channel one. Today. What time do you want to start recording?S: What time is it?U: It’s one forty fiveS: Set the clock to two forty fiveU: Okay, set the clock. Two forty five, is that correct?S: Yes.U: Okay. The clock was set. Returning to timer recording. So,

what time do you want to start recording?U: eight thirty to nine thirtyS: Okay. Starting at eight thirty. Ending at nine thirty. The

program has been added.

Page 45: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

46

Gu Dialogue Systems Lab

Task and question accommodation in AOD

S> Lets see. What can I do for you?U> channel five today

S> Alright. add a program… Lets see. Okay. channel five… today… What time do you want to start recording?

U> from six thirty to seven thirtyS> Okay. from six thirty… to seven thirty… The

program has been added. ”

Signals accommodation(sequencing ICM)

Page 46: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

47

Gu Dialogue Systems Lab

7. Multilinguality and multiple domains

• Language and domain resources can be switched on the fly

• Does not affect the rest of the system

• Thanks to modularity structure of system

Page 47: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

48

Gu Dialogue Systems Lab

Multilinguality

S> Lets see. What can I do for you? U> add programS> Okay. Do you want to add a program?U> yesS> Lets see. What channel do you want? U> svenskaS> Okej. S> Gå tillbaks till lägg till ett program. Vilken kanal vill du spela

in? U> kanal ettS> kanal ett , är det korrekt? S> Så, Vilken kanal vill du spela in? U> englishS> Okay...

Page 48: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

49

Gu Dialogue Systems Lab

Multiple application domains

S> Welcome to the VCR manager! S> Lets see. What can I do for you? U> change domainS> Okay. change domain… Lets see. What domain do you

want? U> telephoneS> Okay. This is your automatic telephone operator… Lets see.

Please specify a function. U> callS> Okay. make a phone call.S> Lets see. Please specify the destination of the call. U> luisS> Okay. Luis… Calling

Page 49: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

50

Gu Dialogue Systems Lab

8. Conclusions: GoDiS & Issue-Based Dialogue Management

• general solutions to– dealing with multiple tasks– sharing information between tasks– grounding and feedback– user initiative (accommodation)– menu-based dialogue

• rapid prototyping of applications– dialogue plans

• switching language and domain online

Page 50: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

51

Gu Dialogue Systems Lab

Current and future work• Extend to more complex dialogue types

– Negotiation (theory exists, not yet implemented)– Tutorial dialogue– …

• Explore use of QUD and ISSUES to assign proper focus intonation – Stina Ericsson, forthcoming PhD thesis

• Build VCR control application, available on the phone– Users can phone up and get TV programs recorded on a

computer– Collect corpus to use as basis for further developments

• Integrate with type-theoretical situation semantics

Page 51: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

52

Gu Dialogue Systems Lab

Future dialogue systems research in Göteborg

• TALK project – Talk and Look, Tools for ambient linguistic

knowledge

• Multilingual dialogue systems– grammar synchronisation– relating abstract domain representations (e.g.

for devices) to natural language expressions

• Extending to multimodal dialogue systems– language representations vs tables, graphics

Page 52: Gu Dialogue Systems Lab 1 Issue-based Dialogue Management in GoDiS Staffan Larsson Dialogsystem HT 2004

53

Gu Dialogue Systems Lab

• Automatic generation of dialogue systems from domain/device descriptions

• Improving speech recognition by looking at dialogue information states

• Multiple recognition grammars/statistical models


Top Related