Download presentation
Presentation is loading. Please wait.
1
Grounding in dialogue systems Staffan Larsson Inst. för lingvistik, GU sl@ling.gu.se OFTI 2002, Göteborg
2
Overview Background Interactive Communication Management (ICM) Action levels and metaissues Feedback properties Update strategies ICM and grounding for a dialogue system
3
Background Research on dialogue and dialogue systems –TRINDI (1997-2000) –SDS (1997-1998) –SIRIDUS (2000-2002) –D’Homme (2001) Implementation –TrindiKit: toolkit for building dialogue systems, information state approach –GoDiS: dialogue system; issue-based dialogue management; implemented using TrindiKit
4
GoDiS in SIRIDUS explore and implement issue-based dialogue management –adapt Ginzburg’s KOS to dialogue system (GoDiS) and implement –extend theory to handle more flexible dialogue (incl. grounding, accommodation, action-oriented dialogue, negotiation, conditional responses) –implement extensions separating general and domain-dependent phenomena helps reconfigurability –general theory of dialogue –extended into subtheories for different dialogue genres –domain knowledge clearly separated –minimize effort for adapting to new genres and domains
5
TrindiKit GoDiS GoDiS-I GoDiS-A Travel Agency Auto- route Xerox manual VCR manager basic IBDM home device manager IS approach action- oriented IBDM T.A. domain knowledge inquiry- oriented IBDM
6
Basic issue-based dialogue management dialogue is, basically, all about raising and addressing issues –incl. short answers –issue reraising and accommodation starting point: KOS framework [Ginzburg] –Dialogue Gameboard (DGB) –related DGB update protocols dialogue moves: ask, answer, (greet, quit) other features –dialogue plans –handling multiple simultaneous issues –information sharing between plans initial genre: enquiry-oriented dialogue (database search) sample domain: travel agency
7
Interactive Communication Management [Allwood] feedback –purpose: regulate grounding (adding to common ground) [Clark] –feedback moves reflect grounding status of utterances turntaking ICM –purpose: regulate turntaking –turntaking moves reflects turntaking structure of dialogue sequencing –purpose: coordination of common ground other than grounding indicating ”internal” mental moves affecting common ground –sequencing moves reflects dialogue structure (part of common ground)
8
Action levels in dialogue [Allwood, Clark] contact perception understanding acceptance
9
Action levels and associated metaissues A uttered U to B; –A and B are now faced with a number of issues contact: –do A and B have contact? perception: –A: does B percieve U (correctly)? –B: what did B say? / Did B say V? understanding: –A: does B understand U (correctly) –B: what did B mean? / Did B mean C? acceptance –A: does B accept U –B: should I accept U?
10
Grounding and action levels ”To ground a thing … is to establish it as part of common ground well enough for current purposes.” [Clark] grounding applies to all action levels –not just understanding U is grounded on level L iff –the grounding issue on level L is positively resolved grounding assumptions correspond to information state updates in system
11
Feedback polarity [Allwood et al ’91] polarity: positive, negative –indicating e.g. understanding (+) or lack thereof (-) eliciting/non-eliciting (evocative/non-evoc.) –whether utterance introduces obligation to respond Examples –”What do you mean?” negative, eliciting –”Do you mean that the destination is Paris?” ??negative??, eliciting –”To Paris.” positive, non-eliciting –”Pardon?” negative, eliciting
12
Form and content of ICM dialogue moves Form: –declarative: ”I didn’t hear what you said.”; ”The destination city is Paris.” –interrogative: ”What did you say?”; ”Do you want to go to Paris?” –imperative: ”Please repeat your latest utterance!” –elliptical interrogative: ”Paris?”, ”To Paris or from Paris?” declarative: ”To Paris.” Content: –object-level: ”To Paris?”, ”Do you want to go to Paris?” –metalevel: ”Did you mean you want to go to Paris?” –none (except polarity): ”Pardon?”, ”OK”
13
ICM in GoDiS Grounding moves –all four action levels –simplified polarities –coarse-grained semantics –no detailed account of form; template-based generation Sequencing moves –reraising issues –loading dialogue plans –question accommodation Turntaking moves –no account of turntaking moves; strict turntaking enforced
14
Feedback polarities in GoDiS how far can we get with meta-issues? –we don’t model obligations –all feedback introduces or answers meta-issues –meta-issues may or may not be responded to; system must be able to deal with both 3 ”polarities”, mutually exclusive –positive: pos implicitly introduces question such as ”was p a correct interpretation of U?” –negative: neg answers question such as ”did B understand U?” –eliciting->interrogative: int explicitly raises question, e.g. ”What does U mean?”
15
Some ICM dialogue moves feedback –icm:Level{*Polarity}{:Content} –icm:und*neg – ”I don’t understand” –icm:und*pos:P – ”To Paris.” –icm:und*int:Q – ”Did you mean to Paris or from Paris?” –icm:acc*neg:Q – ”Sorry, I can’t answer Q” –icm:acc*pos – ”Okay” sequencing –icm:Type{:Content} –icm:reraise:Q – ”Returning to the issue Q” –icm:loadplan – ”Let’s see…”
16
Implicit feedback Clark: ”relevant followup” to U –what is relevant? simple cases for followups to questions: –answer to question –”subquestion” in general, complex inference and knowledge may be needed (implicatures) –counts as positive feedback? –irrelevant followup counts as negative? What about no followup at all?
17
System feedback for user utterances contact –negative (”I didn’t hear anything from you.”, ”hello”) perception –negative: fb-phrase (”Pardon?”, ”I didn’t hear what you said”) –positive: repetition (”I heard ’to paris’”) understanding –negative: fb-phrase (”I don’t quite understand”) –positive: reformulation (”To Paris.”) –interrogative: reformulation (”To Paris, is that correct?”, ”To Paris?”) acceptance/integration –negative: fb-phrase with reformulation (”Sorry, I cannot answer Q”, ”Sorry, Paris is not a valid destination city.”) –positive: fb-word (”Okay.”)
18
User feedback for system utterances contact: - perception –negative: fb-phrase (”Pardon?”, ”I didn’t hear what you said”) understanding: - acceptance/integration –negative (for questions): fb-phrase (”I don’t know”, ”Never mind”) –positive: fb-word (”okay.”)
19
Grounding update strategies strategic questions: –When should U assumed to be grounded on level L? as soon as it has been uttered (of course, the hearer cannot assume grounding until grounding wh-issues have some answer, e.g. ”what did A say?” ) if B does not give negative feedback when B gives positive feedback when B has given eliciting feedback which has been confirmed by A –What to do if the grounding assumption turns out to be mistaken
20
Grounding update strategies cont’d optimism on level L: –assume U is grounded on level L as soon as U has been uttered cautious optimism: –make sure the optimistic assumption can easily be retracted pessimism: –don’t assume U grounded until there has been some positive feedback (or at least no negative feedback)
21
Meta-issue: understanding Ginzburg’s content question –?x.content(LU,x) –”What’s the meaning of LU?” understanding-issue –for speaker who uttered LU with move type m, content c –or hearer who interpreted LU –?und(m(c)) –”Is m(c) a correct interpretation of LU?
22
Optimistic approach to grounding assumption that answer to grounding questions are positive for system utterances –need to deal with cases where user indicates optimistic assumption is wrong –at least for perception and acceptance levels for user utterances –need to indicate failure, and on which action level –if fail to understand or accept, don’t modify SHARED
23
optimistic understanding update input inter- pret updateselect gene- rate output PRIVATE : PLAN : stackset( Action ) AGENDA : Queue( Action ) SHARED : BEL : set( Prop ) TMP : (same type as SHARED) COM : set( Prop ) QUD : stack( Question ) LU: SPEAKER: Speaker MOVES: OQueue( Move ) LATEST-MOVES: Set(Move) LATEST-SPEAKER: Speaker
24
Meta-issue: acceptance Ginzburg’s protocols for acceptance LM = ask Q -> consider ?MAX-QUD(Q) –if yes, push Q on QUD –otherwise, address ?MAX-QUD(Q) LM = assert P -> consider ?MAX- QUD(?P) –if yes, consider ?P if yes, add P to FACTS otherwise, address ?P –otherwise, address ?MAX-QUD(?P)
25
optimistic acceptance update PRIVATE : PLAN : stackset( Action ) AGENDA : stack( Action ) SHARED : BEL : set( Prop ) TMP : (same type as SHARED) COM : set( Prop ) QUD : stack( Question ) LU: SPEAKER: Speaker MOVES: assocSet( Move )
26
choice of strategies in system system utterances –optimistically assumed to be grounded on all levels –negative feedback on perception or acceptance levels -> backtrack to saved state user utterances –if problem on any level, give corresponding negative fb if several alternatives available, give interrogative fb –if OK on all levels, update strategy and feedback determined by recognition score –S > 0.9 optimistic update, icm:acc*pos –0.9 >= S > 0.8 optimistic update, icm:acc*pos, icm:und*pos:Content –0.8 >= S >0.5 pessimistic update, ask(?Content) if ?Content recieves answer ”yes”, add assume Content grounded
27
optimistic acceptance assume positive answer to ?MAX-QUD(Q) assume positive answer to ?MAX-QUD(?P) and ?P we don’t need to represent these issues explicitly for system utterances –need to deal with cases where user indicates optimistic assumption is wrong –so far, only for system questions for user utterances –need to indicate when optimistic assumption is wrong –both questions (sys has no plan) and propositions (invalid database parameter)
28
S> Welcome to the travel agency! U> price information please S> OK, you want to know about price, is that correct? icm:acc*pos icm:und*int:?issue(price) U> yes S> Lets see. How do you want to travel? U> by flight S> OK, by flight. What city do you want to go to? icm:acc*pos icm:und*pos:means_of_transport(fly) … U> do I need a visa ? … S> Lets see. What country are you from? icm:loadplan U> sweden S> Okay. You are a citizen of Sweden. Yes, you need a Visa. S> Returning to the issue of price… icm:reraise:?x.price(x) … S> What month do you want to leave? U> Don’t know icm:acc*neg …
29
Recommended reading! Staffan Larsson (2002): Issue- based Dialogue Management. PhD Thesis. Download the system –www.ling.gu.se/~sl/Thesis SIRIDUS project –www.ling.gu.se/projekt/siriduswww.ling.gu.se/projekt/siridus
30
rejections rejection of question Q –inability to answer Q ”Sorry, I can’t answer that question” –unwillingness to answer Q ”I don’t want to discuss that” rejection of proposition as issue –unwillingness to discuss whether ?P ”I don’t want to discuss that” –other reasons? rejection of proposition –”Sorry, I don’t agree.”, ”You’re wrong!”, ”That’s impossible!” –can be expected to lead to argumentation
31
problematic cases S: ”Where do you want to go?” U1: ”Nowhere” U2: ”I don’t know” U3: (silence) OR ”I want first class!” do these count as rejections? –U1: negative answer? presupposition failiure? rejection? –U2: rejection? but not as definite as ”No comment!” –U3: rejection? in any case, irrelevant followup
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.