Intention & Cooperation Discourse and Dialogue CS 359 October 18, 2001
Jan 21, 2016
Intention & Cooperation
Discourse and Dialogue
CS 359
October 18, 2001
Questions
• Do systems do conversational implicature?
• What sorts of knowledge representations are used in dialogue systems?
• Are there systems that incorporate planning, dialogue act recognition?
• Has anyone tried applying these techniques to other conversational styles - e-mail, IM?
• 60-80% accurate subsystems, how bad is the whole thing?
Dialogue Management:Reading & Reporting
• Dialogue Management overview
– Spoken Dialogue Technology, McTear
• State based systems
– Design issues (McTear)
– Automatic learning (Woszczyna & Waibel)
• Frame-based systems: SunDIAL (Peckhem at al)
• Plan based systems
– Theorem proving (Smith et al)
– TRAINS (BDI): Allen et al
– Rational Agency “Artimis” - Sato & de Mori
Roadmap
• Structure of Discourse (G&S 1986)– Attention to Intention
• Planning and Cooperation– Cooperative meaning: Grice’s Maxims– Cooperative action:
• STRIPS planning basics
• Shared plans
• Discourse and Domain plans
Discourse Structure
• Attentional Structure:– Focus– Reference– Information Structure: Given/New
• Intentional Structure:– Discourse purpose (DP)
• Discourse segment purpose (DSP)• Contribute to overall goal of conversation
• Linguistic structure organizes/executes
Cooperation in Communication
• Conversational participants act together– Speakers must provide sufficient information
about beliefs and intentions for hearers to interpret as part of plan
– Hearers must recognize cues in language and structure of discourse to constrain inference of plan
Cooperative Meaning
• Cooperative Principle: Grice 1975– Make conversational contribution as required at
stage of discourse by accepted discourse goal
• Maxims:– Quantity – Quality– Relation– Manner
Maxim of Quantity
• Be as informative as necessary– Be no more informative than necessary
• E.g.”I saw three ducks”->– “I saw EXACTLY three ducks”
Maxim of Quality
• Do not say that which you believe to be false– Don’t say things without evidence
• E.g. “I saw ducks” implicates that you really did
Maxim of Relation
• Be relevant– Utterances should relate to each other and
overall discourse goals– Focus, coherence, reference all rely on relation
• E.g. A:I am out of gas.
• B:There’s a garage around the corner.
Maxim of Manner
• “Be perspicuous”– Avoid ambiguity– Avoid obscurity– Be brief– Be orderly
Maxims and Meaning
• In cooperative discourse, expect maxims will be followed.
• However,– Violate or “opt out”– One or another may be violated in case of clash– Flout: Deliberately, blatantly break
• “Exploit” maxim to create conversational implicature– Meaning outside of literal sense
• E.g. irony, metaphor, hyperbole, etc...
Planning & Plan Recognition
• Discourse planning based on classic AI– STRIPS (Nilson et al)
• Plan: Sequence of actions from start to goal• Action model: “Operator”
– “IF”: precondition for action– “ADD”,”DELETE”: effect on state of action– “BODY”: subactions
• Recognition: Links beliefs & desires to preconditions and goals
Plan Example
Planning Issues
• Complexity– Forward-chaining: simple, but exponential– Backward-chaining: Can reduce search
• Assumes single actor, single plan– Full control- ‘master-slave’
• Need notions of generation, enablement, simultaneous action, maintenance
Shared Plans
• Tie belief and intention to plans (Pollack 86)– Beliefs about: relations among actions
(enablement, generation) and executability– Intentions (of agent) about actions
• Multiple collaborative agents• Not just simultaneous private plans• Belief => Mutual belief• Different agents, different actions
Collaborative Plans
Plan => Shared Plan
• SimplePlan(G,an,[a1..an-1],t1,t2)• BEL(G,EXEC(ai,G,t2),t1)
• & BEL(G,GEN(ai,ai+1,G,t2),t1) • & INT(G,ai,t2,t1)• & INT(G,BY(ai,ai+1),t2,t1)
• BEL: Believe• INT: Intend• EXEC: Execute• GEN: Generate• BY: By
• SharedPlan(G1,G2,A)• MB(G1,G2,EXEC(aj,Gaj)
• MB(…)
• MB(G1,G2,INT(Gaj,aj))
• MB(G1,G2,INT(Gaj,BY(aj,A))
• INT(Gaj,aj)
• INT(Gaj,BY(aj,A))
Cooperative Plan Maxims
• Conversational Default Rule1 (CDR1)
• MB(G1,G2,Desire(G1,P) &– Cooerative(G1,G2,P) &– Communicating (G1,G2,Desire(G1,P)
• MB(G1,G2,Desire(G1,
• Achieve(SharedPlan(G1,G2,Achieve(P))))
•
Cooperative Plan Maxims
• Conversational Default Rule 2 (CDR2)• SharedPlan* = Partial Shared Plan• [SharedPlan*(G1,G2,Achieve(P)) &• MB(Desire(G1,Do(G2,Action)) &• MB(G1,G2,Exec(G2,Action) &• MB(G1,G2,Contribute(Action,Achieve(P)))]• Intend(G2,Action) &• MB(G1,G2,Intend(G1,G2,Intend(G2,Action)|)
Action Schemas
• Simultaneous action
• Conjoined actions
• Sequential actions
• Single Actor plans
Shared Plan Summary
• Intentional structure– Intentions
• Relations: Dominance, Satisfaction-precedence
– Discourse segments correspond to intentions
• Plans in collaborative, task-oriented discourse– Not fixed, negotiated– Intended to be recognized– Propose plan; accept/deny; refine beliefs,
intentions,plans,.,
Limitations of Shared Plans
• Only handles domain planning– No treatment of discourse plans
• Turn-taking, clarification, openings…
• Only addresses intentional structure– Doesn’t integrate attentional structure
• Information flow, focus, reference
Proposal: Unified Framework
• Integrate disparate components of discourse theory– Semantics: accessible referents– Attentional state– Intentional structure
• Common structures form”threads”,”scripts”
– Speech acts - functional, informational– Dialogue acts
DRT-Style Combined StructureA: There is an engine at AvonB: It is hooked to a boxcar.
ce1 ce2 s s’ s’’
x w ece1: asrt(A,B,engine(x) (s) (s’))
Avon(w)e:at(x,w)y u e’
ce2: asrt(B,A, boxcar(y) (s’) (s’’))e’:hook(y,u)
u is x
Conversation Acts
Discourse Level Act Type Sample Acts
Sub-utterance Turn-taking Take-turn, keep-turn, assign-turn
Utterance Unit Grounding(Acknowledge)
Initiate, continue,ack, repair, cancel
Discourse Unit Core Speech Acts Inform,ynq,check,eval, accept
MultipleDuscourse Units
Argumentation Elaborate, clarify,Convince, q&a
Mental States & Dialogue Acts
• Incorporate mental states in “s” of structure– Encode belief, attention, obligation..– Belief = MB– Situation S’ inherits all of S
• Dialogue Acts– Statement (assert), Open-option, Offer, Commit– Acts bring about effects
• Me; ntal states, event types
• E.g. Commit -> Obliged
Threads
• Intentional organization:– Events grouped into “threads”
• Threads “dominate” events
• Events are ordered
• Identify specific thread types– Argumentation acts= rhetorical relations: RST
• Elaboration, etc
– Predictable: activities - “scripts”,• Known conversational styles
• Provide expectations, predict subsequent moves
Summary
• Discourse as collaboration– Gricean conversational maxims
• Cooperative principle
– Cooperative task-oriented plans• “SharedPlan’
• Use mutual belief, negotiation of plan, act timing
• Integrated discourse model– Combine semantics, attentional, intentional state,
conversational act strategy
Challenges
• Conversational act recognition– “Okay’
• Domain plan recognition– Collection
Conversation Acts
Extend speech acts for conversational control