A framework for modeling the relationships between the rational and behavioral reactions of assisting conversational agents François Bouchet Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI December 18th 2009 EUMAS 2009
Introduction Agent architecture Case study: Cognitive Biases Conclusion Outline Introduction 1 Agent architecture 2 Case study: Cognitive Biases 3 Conclusion 4 François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Outline Introduction 1 Context: Assisting agents with a cognitive model Towards rational and behavioral ACA experimentation Agent architecture 2 Case study: Cognitive Biases 3 Conclusion 4 François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Context: Assisting agents with a cognitive model Assisting Conversational Agents (ACA) Issues of assistance to novice users “Paradox of motivation” (Carroll & Rosson, 1987) Users prefer the help provided by “a friend behind the shoulder” (Capobianco & Carbonell, 2001) A solution: conversational agents for assistance “Persona Effect”: an animated agent increases credibility (Lester, 1997) Natural language: ideal modality when facing cognitive distress (Carbonell, 2003) François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Context: Assisting agents with a cognitive model Realistic Assisting Conversational Agents To be used, must look like “the friend behind the shoulder”: Embodiment: movements, emotions rendering. . . → suitable with its visual realism – or risks to fall into the “Uncanny valley” (Mori, 1970) Cognitively: coherent personality, credible reactions to requests. . . → suitable with its embodiment – or risks to reproduce the “Clippy Effect” (Xiao et al., 2004) François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Towards rational and behavioral ACA experimentation Typical ACA architecture User interface (I) Assisting Agent (A) R ti Rational l Model of M d l f Translation Engine ( ξ r) assistance (M) Natural Language « Textual requests » GUI events Processing (NLP Chain) (NLP ‐ Chain) Formal Heuristics Resource files Request (in FRL) Multimodal inputs/outputs Application DOM structure reasoning reasoning Modeling files Modeling files Expression Dialogical etc. session Natural Language and « Textual answers » User Formal Gestural answers Non ‐ verbal behavior Browsing Answers GUI events (NLE Chain) (NLE ‐ Chain) (in FRL) (in FRL) DOM-Integrated Virtual Agents (DIVA) (Xuetao et al., 2009) François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Towards rational and behavioral ACA experimentation Typical ACA architecture issues Issue: Lack of human-likeness and dialogue naturalness 1 Repetition of cooperation: the agent is always responsive 2 Repetition of answer’s schemes: use of similar linguistic patterns 3 Repetition of rational reactions: independently from previously asked requests Solution: a modified architecture a personality model integrated tp the model of assistance M a correlated behavioral engine E b working with E r François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Towards rational and behavioral ACA experimentation Typical ACA architecture issues Issue: Lack of human-likeness and dialogue naturalness 1 Repetition of cooperation: the agent is always responsive 2 Repetition of answer’s schemes: use of similar linguistic patterns 3 Repetition of rational reactions: independently from previously asked requests Solution: a modified architecture a personality model integrated tp the model of assistance M a correlated behavioral engine E b working with E r ⇒ Relationship between E r and E b ? To define through experimentation with Rational and Behavioral (R&B) agents François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Outline Introduction 1 Agent architecture 2 Formal Request Language (FRL) Model of Assistance M Mind model M . Ψ Heuristics Case study: Cognitive Biases 3 Conclusion 4 François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion General R&B agent architecture Model Rational Agent User Session Topic Behavioral Heuristics Heuristics Heuristics Heuristics Mind H Hr i Hb Hb i User’s formal FRL request request Rational Behavioral Query Scheduler Engine Engine Agent’s formal FRL answer answer Detailed model of assistance M (including agent’s mind) Separated heuristics as symbolic representation Behavioral Engine E b A query scheduler François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Formal Request Language (FRL) Language structure FRL supports I/O between the H r H b M A U S T Y user (u) and the agent (a) through the interface FRL E r E b QS FRL Form: PERFORMATIVE[ content ] Content Reference (R): element of the model M Action (A): operation executable in the environment Proposition (P): logical proposition regarding the state of M Value (V): value of an element of the model M Performatives François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Formal Request Language (FRL) Language structure FRL supports I/O between the H r H b A S T M Y U user (u) and the agent (a) through the interface FRL E r E b QS FRL Form: PERFORMATIVE[ content ] Content Performatives Knowledge: ASK u [ R|A|P ] , HOW u [ A ] , . . . Actions management: SUGGEST a [ A|P ] , . . . Feeling expression: FEEL u [ P ] , LIKE a [ R|A|P|V], . . . Dialogue: AGREE u [P] , BYE u [] , . . . François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Model of Assistance M Syntax Tree structure H r H b M A Y U S T Non-terminal nodes: concepts FRL Terminal nodes: symbols, E r E b QS FRL numbers, booleans, strings Skeleton of the M ontology 5 domains in the model M : Model = Rootconcept[ 1 The agent ( A ) Concept1[ 2 The user ( U ) Concept11[...], Concept12[...], 3 The request ( R ) ...] 4 The session ( S ) Concept2[ Concept21[...], 5 The topic ( T ) Concept22[...] M = < A , U , R , S , T > ...], ...] François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Model of Assistance M Dynamics M 0 = < A 0 , ∅ , ∅ , ∅ , T 0 > H r H b A S T M Y U Agent updates A , U , R and S according to interactions FRL E r E b QS FRL Application updates T Model Query Language (MQL) GET[ path ] return subtrees SET[ path,expr ] replaces subtree by expression ADD[ path,expr ] appends expression to the subtree DEL[ path,subtree ] deletes a subtree . . . Example of path: M . A .name A query object Q i wraps queries Q + i / Q − i stands for a successful/failed request François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Mind model M . Ψ Four mental states Unary Binary H r H b M A U S T Y Static Trait Ψ T Role Ψ R FRL E r E b QS FRL Dynamic Mood Ψ m Affect Ψ a Values In [ − 1 , 1 ] but we distinguish 5 intervals: v ∈ [ − 1 , − 0 . 8 ] < strongly antonymic v ∈ [ − 0 . 8 , − 0 . 2 ] - antonymic v ∈ [ − 0 . 2 , 0 . 2 ] = neutral v ∈ [ 0 . 2 , 0 . 8 ] + positive v ∈ [ 0 . 8 , 1 ] > strongly positive François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Mind model M . Ψ Four mental states Unary Binary H r H b M A U S T Y Static Trait Ψ T Role Ψ R FRL E r QS E b FRL Dynamic Mood Ψ m Affect Ψ a Traits Ψ T Classical “Big Five” (Goldberg, 1981) defining the personality Openness : appreciation for adventure, curiosity Conscientiousness : self-discipline and achieves goals Extraversion : strong positive emotions and sociability Agreeableness : compassion and cooperativeness Neuroticism : experience negative emotions easily François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Introduction Agent architecture Case study: Cognitive Biases Conclusion Mind model M . Ψ Four mental states Unary Binary H r H b M A S T Y U Static Trait Ψ T Role Ψ R FRL E r E b QS FRL Dynamic Mood Ψ m Affect Ψ a Moods Ψ m Personality factors changed in time by heuristics and biases Energy : physical strength Happiness : physical contentment regarding the situation Confidence : cognitive strength Satisfaction : cognitive contentment regarding the situation François Bouchet, Jean-Paul Sansonnet LIMSI-CNRS Université Paris-Sud XI
Recommend
More recommend
