Konversationsanalys (CA), och kommunikationsreglering Pragmatik VT04 Staffan Larsson

Conversation Analysis Etnologer: ”etnometdologi” Sacks, Schegloff, Jefferson Empiriska data audio (ofta telefonsamtal) video transkriptioner Empirisk metod Söker efter mönster i data och konstruerar regler för att förklara dessa I motsats till traditionell lingvistik & pragmatik: intuitioner, filosofisk spekulation, ”armchair linguistics” (Relativt) ickeformell metod

Typer av mönster funna inom CA makrostrukturer Närhetspar (Adjacency pairs) Preferensorganisation Presekvenser (Pre-sequences) ”local management systems”: lokal reglering (subdialoger) Turtagning Reparationer

Närhetspar (adjacency pairs) Sekvenser av 2 yttranden som är näraliggande och produceras av olika talare Del 1 föregår del 2 Dock ej nödvändigtvis direkt efter Exempel fråga-svar hälsning-hälsning erbjudande-accepterande Liknar dialogspel men annan metod ej uttryckt i grammatikform; ”lösare” struktur Approximativ regel: Om A producerar den första delen i ett närhetspar, måste A sluta tala och B måste producera parets andradel Alternativ regel: konditionell relevans Om A producerar den första delen i ett närhetspar, så är dess andradel förväntad och relevant

Preferensorganisation Problem med närhetspar: till varje förstadel svarar en mängd potentiella andradelar T ex fråga -> svar protest vidarebefodring (”Fråga Kalle”) vägran att svara ifrågasättande av ärlighet Lösning: preferensorganistation vissa andradelar är prefererade

preferens är ej ett psykologiskt begrepp utan relaterat till ”markedness” prefererade andradelar är omärkta, ickeprefererade är märkta Vanliga kännetecken på ickeprefererad andradel: föregås av försening, tvekljud etc inledningsord som makerar ickepreferens (”Well...”, ”Tja...”) åtföljs av förklaring till varför prefererad andradel ej gavs innehåller avböjande komponent Exempel A: Kan du hjälpa mig? B1: visst (prefererat) B2: Äh njae jag har lite mycket att göra just nu

Pre-sekvenser ”förberedande frågor” Exempel 1 Exempel 2 T1 X: Är du upptagen ikväll? T2a Y: Nä, hurså? T3a X: Vill du följa med på bio? Exempel 2 T2b Y: Ja, jag ska tvätta håret. hurså? T3b X: Äh det var inget särskilt? T1 är en förberedande fråga som undersöker ett förvillkor till den handling som T3 gäller T3 beror av T2, responsen på T1

Turtagning Observation: konversation karakteriseras av turtagning (A och B: talare) A – B - A – B – A - ... Hur åstadkoms denna organisation? mindre än 5% överlapp Med hjälp av ett ”Local Management System”! en uppsättning regler styr tillgång till ”the floor”, ung. rätten att tala

Turtagning: begprepp Tur (Turn Constructional Unit) en sekvens av syntaktiska enheter vars gränser (främst) avgörs av syntaktiska (t ex satsgränser) eller prosodiska faktorer TRP = Transition Relevance Place en punkt där turtagning kan ske TRP måste vara möjliga att förutse, för att smidig turtagning ska vara möjlig

Regel 1: Gäller initialt vid första TRP i varje tur (a) Om aktuell talare (A) väljer nästa talare (N) under sin tur, måste A sluta och N börja tala vid första TRP efter valet av N (b) Om A inte väljer N så kan vem som helst ta turen vid nästa TRP (fri konkurrens) (c) Om A inte väljer N och ingen annan ”självväljer” så kan A fortsätta Regel 2: Gäller vid efterföljande TRP i en tur När 1(c) har applicerats av A, så gäller 1(a)-(c) vid nästa TRP, och rekursivt vid efterföljande TRP, tills talarbyte inträffar

Om någon bryter mot reglerna den som avbryter kan bli förmål för kritik (”Låt mig tala till punkt!”) ”tävling”: ökande volym, lägre tempo, förlängda vokaler, staccato etc. tills någon ger upp Kritik mot denna modell Tar ej hänsyn till ickeverbala signaler Vad är en TRP mer exakt? Ej universell Tar ej hänsyn till sociala roller & maktstrukturer institutionella turtagningssystem (t ex formella möten, rättegång)

Turtagning i dialogsystem Strikt turtagning: Så länge systemet talar så kan användaren inte säga något (systemet lyssnar inte) Så länge användaren (utan paus) talar gör systemet inget; vid paus tar systemet över turn ”Barge-in”: Om användaren säger något då systemet talar så slutar systemet tala Turtagning i dialog med flera deltagare, inklusive dialogsystem (Fredik Kronlid)

Reparationer Exempel Next Turn Repair Initiator (NTRI) A: Jag mötte Nils igår TUR1 B: Vem sa du? [NTRI] TUR2 A: Nils TUR3 Next Turn Repair Initiator (NTRI) inbjuder till reparation av föregående tur Typer av reparationer Självinitierad, utan NTRI Annan-initierad, med NTRI Preferensordning Självinitierad i TUR1 Jag mötte Nils äh Kalle igår Själviniterad efter TUR1 men före TUR2 Jag mötte Nills igår. Äh Kalle mena ja Annaninitierad med NTRI i TUR2, självreparation i T3 (se överst) Annaniniterad annanreparation i T2 A: Jag mötte Nils igår B: Du menar väl Kalle?

Grounding (Clark mfl) Not CA, but related area Common Ground (CG): shared knowledge about the dialogue; utterances incrementally add to CG ”To ground a thing … is to establish it as part of common ground well enough for current purposes.” (Clark) making sure that the participants are percieving, understanding, and accepting each other’s utterances Grounding is regulated by local communication management systems (Allwood) ICM: grounding, sequencing, turntaking OCM: hesitations, self-corrections, ...

Clark’s grounding model Contribution types: Present, Accept When does the presentation phase end? I: Move the boxcar to Corning I: and load it with oranges R: ok S Present 1 Accept F

Clark’s grounding model Contribution types: Present, Accept When does the presentation phase end? I: Move the boxcar to Corning R: ok I: and load it with oranges Cannot be decided by just looking at the utterance; need to look at next utterance not useful in realtime setting S Present 1 Accept F

Traum’s grounding model Discourse Units (DUs) unit of conversation at whicgh grounding takes place composed of individual utterance-level actions (grounding-level acts, sub-DU acts) Some (sub-DU) acts Initiate Continue Ack(nowledge) Repair: correcting oneself or the other Cancel: retraction, makes DU ungroundable (”Äh förresten det var inget”)

act(I/R); I=initiator, R=responder This model is supplemented with an information state update model Continue(I) S Initiate(I) 1 Ack(R) F

adding self-repair and cancel Continue(I), Repair(I) S Initiate(I) 1 Ack(R) F Cancel(I) Cancel(I) D

adding self-repair and cancel Continue(I), Repair(I) S Initiate(I) 1 Ack(R) F Cancel(I) Cancel(I) D

Feedback and grounding in dialogue systems

Overview Interactive Communication Management (ICM) ”Verification” in dialogue systems Classifying and formalising feedback Feedback moves for GoDiS Issue-based grounding Formalising sequencing moves for GoDiS Conclusions & Future work

ICM (Allwood) Interactive Communication Management Feedback moves As opposed to Own Communication Management (OCM): self-corrections, hesitations, etc. Feedback moves (short) utterances which signal grounding status of previous utterance (”mm”, ”right”, ”ok”, ”pardon?”, ”huh?” etc.) Sequencing moves utterances which signal dialogue structure (”so”, ”now”, ”right”, ”anyway” etc.) Turntaking moves

ICM in current commercial systems Usually, limited to ”verification” Examples (San Segundo et. al. 2001) I understood you want to depart from Madrid. Is that correct? [”explicit v.”] You leave from Madrid. Where are you arriving at? [”implicit v.”] Involves repetition or reformulation Appears in H-H dialogue, but not very common

From verification to ICM in dialogue systems ”Verification” is just one type of ICM behaviour Perhaps the one most cruicial in dialogue systems given poor speech recognition Could a wider range of the ICM behaviour occurring in H-H dialogue be useful in dialogue systems? We want a typology of ICM moves for H-H dialogue Feedback and sequencing moves We want to formalise it and use it in a system Still we will implement only a subset We want to relate it to grounding in a system

Classifying feedback Level of action Polarity Eliciting or non-eliciting Form (syntactic realisation) Content type (object- or metalevel)

Feedback levels Action levels in dialogue (Allwood, Clark, Ginzburg) Contact: whether a channel of communication is established Perception: whether DPs are perciveving each other’s utterances Understanding: Whether DPs are understanding each other’s utterances Non-contextual (”semantic”) meaning Contextual (”pragmatic”) meaning Acceptance: Whether DPs are accepting each other’s utterances The function of feedback is to signal the status of utterance processing on all levels

Feedback polarity Polarity (Allwood et.al. 1992) Examples Positive: indicates contact, perception, understanding, acceptance Negative: indicates lack of contact, perception, understanding, acceptance We add a ”neutral” or ”checking” polarity – there is one or more hypotheses, but the DP lacks confidence in them Examples ”I don’t understand”: negative ”Do you mean that the destination is Paris?”: checking ”To Paris.”: positive ”Pardon”: negative

Eliciting / nonelciting feedback (Allwood et. al. 1992) Eliciting feedback is intended to evoke a response from the user Noneliciting feedback is not so intended But may nevertheless recieve a response Rough correspondence / operationalisation Checking feedback is eliciting; explicitly raises grounding issue Positive feedback is noneliciting; may implicitly raise grounding issue What about negative feedback? ”pardon?”,”huh?”: eliciting? ”I didn’t hear you”: noneliciting?

Object- or metalevel content Utterances with metalevel content explicitly refer to contact, perception, understanding or acceptance Object-level utterances instead refer to the task at hand Example S: What city are you going to? U: Paris S(1a): Did you say you’re going to Paris? [meta] S(1b): Are you going to Paris? [object] S(2a): Do you mean Paris, France or Paris, Texas? S(2b): Do you want to go to Paris, France or Paris, Texas? This dimension does not apply to all feedback, e.g. ”Paris.”, ”Pardon?” (Is 2b feedback or simply an alternative question?)

Realisation of feedback moves Syntactic 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.” In general, the exact formulation of ICM phrases may depend on various contextual factors including activity, noise level, time constraints etc.

Simplifying assumptions regarding feedback We only represent action level and polarity Eliciting/noneliciting dimension implicit Negative feedback is eliciting in some sense; since something went wrong, it must be fixed Checking feedback is also eliciting, since it poses a question that must be adressed Positive feedback is not eliciting (we assume) Syntactic form not included in classification; decided by generation module Metalevel / object level perhaps not so interesting unless full compositional semantics are used ”Do you mean that you want to Paris?” vs. ”Do you want to go to Paris?”

Formalising ICM dialogue moves Level con: contact per: perception sem: semantic understanding (no context) und: pragmatic understanding (relevance in context) acc: acceptance Polarity pos: positive neg: negative chk: checking

Feedback move notation icm:Level*Polarity{:Args} Examples icm:per*pos:String – ”I heard you say ’londres’” icm:und*neg – ”Sorry, I don’t understand” icm:und*chk:AltQ – ”Do you mean x or y?” icm:und*pos:P – ”To Paris.” icm:acc*neg:Q – ”Sorry, I can’t answer Q” icm:acc*pos – ”Okay”

GoDiS: an issue-based dialogue system Explores and implements Issue-based dialogue management (Larsson 2002) Based on Ginzburg’s notion of a dialogue gameboard involving Questions Under Discussion (QUD) Uses (mostly pre-scripted) dialogue plans Extends theory to more flexible dialogue Multiple tasks, information sharing between tasks ICM: feedback and grounding, sequencing Question accommodation, re-raising, clarification Inquiry-oriented, action-oriented, negotiative dialogue

System feedback for user utterances in GoDIS contact negative (”I didn’t hear anything from you.”, ”Hello?”) [icm:con*neg] perception negative: fb-phrase (”Pardon?”, ”I didn’t hear what you said”) [icm:per*neg] positive: repetition (”I heard ’to paris’”) [icm:per*pos:String] semantic understanding: negative: fb-phrase (”I don’t understand”) [icm:sem*neg] positive: reformulation (”Paris.”) [icm:sem*pos:Content]

System feedback, cont’d pragmatic understanding negative: fb-phrase (”I don’t quite understand”) [icm:und*neg] positive: reformulation (”To Paris.”) [icm:und*pos:Content] checking: reformulation (”To Paris, is that correct?”, ”To Paris?”) [icm:und*chk:Content] acceptance/integration negative:fb-phrase with reformulation (”Sorry, I cannot answer Q”, ”Sorry, Paris is not a valid destination city.”) [icm:acc*neg:Content] positive: fb-word (”okay.”) [icm:acc*pos]

User feedback for system utterances in GoDiS contact: - perception negative: fb-phrase (”Pardon?”, ”I didn’t hear what you said”) [icm:per*neg] understanding: - acceptance/integration negative: fb-phrase (”I don’t know”, ”Never mind”) [icm:acc*neg] positive: fb-word (”okay.”) [icm:acc*pos]

Feedback selection Feedback polarity selected depending on: Contact: Whether any speech is observed Perception: Speech recognition score > threshold Semantics: Whether system can find a non-contextual interpretation Pragmatic understanding: Whether system can find a relevant contextual interpretation none: extremely high score (certain of interpretation) Positive: high score (pretty sure of interpretation) Checking: medium score (not so sure) Negative: low score (very unsure) Acceptance: Whether system can accept what has been said General principles Produce positive feedback only on highest possible level When producing negative feedback on level N, produce positive feedback on level N-1

Feedback on multiple levels Negative perception feeback 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> siridus S> I heard you say siridus . Sorry, I dont understand. What can I do for you? U> channel one S> channel one. I dont quite understand. Do you want to add a program or change channel? Positive perception Negative understanding Positive understanding (word meaning) Negative understanding (relevance) (Task clarification)

Positive understanding Rejection (negative acceptance feedback) U> turn on the t v S> turn on the TV… Sorry, I cannot control the TV set. Do you want to add a program or change channel?” U> pardon S> Sorry, I cannot control the TV set. Do you want to add a program or change channel? U> change channel S> Okay. User negative perception System repetition Positive acceptance

Reactions to positive and checking feedback After check feedback, (e.g., ”channel one, is that correct?”) positive response is needed, or system will assume it was wrong After positive feedback, (e.g., ”channel one.”) if user gives no response or positive response, system continues to assume it was right; If user gives negative response, system assumes it was wrong correcting the system

Correcting the system S> Lets see. What can I do for you? U> add program S> Okay. Add a program… S> Lets see. What channel do you want? U> channel six S> OK, channel five. U> no S> not channel five. So, What channel do you want? S> Okay. channel six.” Positive feedback Negative answer to fb.

Issue-based grounding Checking feedback on und-level explicitly raises understanding-issue icm:und*chk:C raises ?und(C) ”Is C the meaning of the previous utterance?” Positive response leads to adding C to shared commitments Negative or no response leads to no action Positive understanding feedback does not raise the understanding-issue explicitly In fact, tentatively assumes it has been positively resolved but makes it available for interpretation of short answers in this case, ”yes” or ”no” Negative reponse leads to retracting C Positive or no response leads to no action So far, only implemented for understanding level

ISSUES, QUD and accommdation We distinguish QUD and ISSUES: QUD (local): Questions available for resolution of short answers ISSUES (global): Issues/questions that have been raised but not yet resolved QUD-to-ISSUES accommodation If an answer is given which does not address any question on ISSUES, But does address a question Q on QUD Then, accommodate Q to ISSUES (this amounts to raising Q)

Feedback, ISSUES and QUD Assume previous move had content C Checking feedback Push ?und(C) on ISSUES and QUD Positive feedback Add C to shared commitments Push ?und(C) on QUD (but not on ISSUES) ”yes” or ”no”  do QUD-to-ISSUES accommodation Integrating responses to understanding-issues Done by a single rule, regardless of how the understanding-issue was raised Given that ?und(C) is on ISSUES, ”yes”  add C to shared commitments if not already there ”no”  retract C from shared commitments if it’s there (actually, backtrack to saved previous shared commitments)

Negative response to positive feedback S> Lets see. What channel do you want? U> channel six S> OK, channel five. channel (5) added to shared commitments; ?und(channel (5)) on QUD U> no QUD-to-ISSUES accommodation  ?und(channel (5)) on ISSUES integrate ”no”  retract channel(5) S> not channel five. So, What channel do you want?

Negative response to cheking feedback S> Lets see. What can I do for you? U> add program S> Okay. Add a program… S> Lets see. What channel do you want? U> channel six S> channel five? ?und(channel (5)) on ISSUES and QUD U> no integrate ”no” ( do nothing) S> So, What channel do you want? S> Okay. channel six.”

Sequencing ICM Discourse particles Verbose sequencing ”so” may be used to reraise a previously discussed question ”right”, ”anyway”, ”let’s see…” Verbose sequencing ”Let’s talk about …”, ”Let’s return to the issue of …” How do we classify these? We correlate them with updates to the common ground

Sequencing moves generated by GoDiS Formal notation schema: icm:Type{:Content} Loading a dialogue plan icm:loadplan – ”let’s see.” Question accommodation icm:accommodate – ”alright.” Reraising an issue icm:reraise – ”so, ” icm:reraise:Q – ”returning to the issue of …”

Sequencing ICM: reraising issue, loading a plan Signals loading a plan S> Welcome to the travel agency! U> price information S> (…) Lets see. How do you want to travel? U> by flight S> (…) What city do you want to go to? U> paris S> (…) What city do you want to go from? U> do I need a visa ? S> (…) Lets see. What country are you from? U> sweden S> Okay. Yes, you need a Visa. S> Returning to the issue of price. Lets see. What city do you want to go from? Reraising an issue explicitly

Sequencing ICM: Accommodation 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 thirty S> Okay. from six thirty… to seven thirty… The program has been added. ” Signals accommodation

Future work Replace current ad-hoc forms based on corpus studies and existing work ”discourse markers” (Schiffrin) ”cue phrases” (Grosz & Sidner and others) ”Real” generation rather than templates Integrate ICM with other utterances, rather than just appending them Explore other ways of generating ICM Intonation, facial expression, etc. Extend the range of ICM generated (and interpreted) by the system Extend issue-based grounding to all levels

Summary of ICM and grounding in GoDiS By extending the range of ICM used by systems, their communication becomes more natural and comprehensive We have provided an initial classification of feedback and sequencing ICM useful in a dialogue system, and implemented it Issue-based grounding provides mechanisms allowing the user to react to system feedback Sequencing moves can be correlated with updates to common ground, and used to signal these updates to the user

Relation to Traum’s computational theory of grounding Traum puts focus on positive feedback and corrections (self and other) Deals with the question, when does a contribution end? Related to turntaking. Focus on self- and other-corrections (not included here); involves turntaking and OCM, but also feedback Does not include sequencing ICM Based on the TRAINS corpus of H-H dialogue -> (arguably) focus on positive feedback Focus on understanding-level ”grounding” here refers only to the understanding level Acceptance and rejection seen as ”core speech acts”

Implicit feedback? Clark: ”relevant followup” to U counts as positive feedback What is relevant? simple cases for followups to questions: answer to question ”subquestion” feedback concering question Complex cases: all other utterances In general, complex inference and knowledge may be needed (implicatures) Currently, irrelevant followup counts as negative feedback (a cautious assumption) What about no followup at all? in reaction to ask-move or interrogative feedback, counts as negative in reaction to answer or positive feedback, counts as positive

Rejection? Should these count as rejections? S: ”Where do you want to go?” U1: ”Nowhere” U2: ”I don’t know” Should these count as rejections? U1: negative answer? presupposition failiure? rejection? U2: rejection? but not as definite as ”No comment!”

OCM: Own Communication Management Egenkommunikationsreglering Till nästa gång

Uppgifter 1. Hur fungerar turtagning enligt CA-analysen? Hitta på några dialoger som exemplifierar olika turtagningssituationer och förklara dessa utifrån CA-reglerna för turtagning. 2. Titta i TV-tablån och bestäm dig för ett TV-program som du vill spela in. Ha penna och papper (eller dator) redo. Ring upp Videoapplikationen i GoDiS på 7731978 och försök programmera videon att spela in ditt program. Anteckna allt som sägs i dialogen (det går rätt långsamt, så man hinner med). Vilka typer av ICM (grounding och sequencing) förekommer i dialogen? Observera att systemet funkar rätt dåligt just nu, p g a diverse tekniska problem. GoDiS är egentligen mycket bättre än såhär!

I dialog med en miniräknare Uppgift: Fundera över följande: Hur skulle talad interaktion med en vanlig enkel miniräknare kunna se ut? Aspekter att fundera över: Turtagning Tvekljud Självreparation Återkoppling Innan torsdagens föreläsning: Försök att designa ett ‘dialogspel’ som inbegriper dessa fenomen! Ge konkreta exempel i form av små transkriptioner, t.ex.: U: 2+2 +1 va? S: 4 5 5 Skriv en sida om din design. De som gör detta tillräckligt bra slipper fler uppgifter i samband med min föreläsning. Talsyntes Taligenkänning