34
RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek , ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder, DFKI, Saarbrücken Martine Grice, IPUS, Saarbrücken Stefan Baumann, IPUS, Saarbrücken Hannes Pirker , OFAI, Vienna

RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Embed Size (px)

Citation preview

Page 1: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

RRL: A Rich Representation Language

for the Description of Agent Behaviour in NECA

Paul Piwek, ITRI, BrightonBrigitte Krenn, OFAI, Vienna

Marc Schröder, DFKI, Saarbrücken Martine Grice, IPUS, Saarbrücken

Stefan Baumann, IPUS, Saarbrücken Hannes Pirker, OFAI, Vienna

Page 2: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,
Page 3: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

NECA

Duration: 2.5 years

Start: October 2001

A new generation of mixed multi-user / multi agent virtual spaces for the internet

Populated by affective conversational agents

Page 4: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Affective Conversational Agents

• Express themselves through

– Emotional speech and – synchronised non-verbal expression

Page 5: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Application Scenarios

Socialite– a multi-user web-application in the social

domain eShowRoom – a novel approach to the presentation of

products in e-Commerce applications

The NECA Platform will be evaluated in two concrete application scenarios

Page 6: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Socialite

Page 7: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,
Page 8: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

NECA’s Architecture

Scene Generator

User Input

Scene Description

Affective Reasoner (AR)

Page 9: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

NECA’s Architecture

Scene Generator

User Input

Scene Description

Multi-modal Output

Multi-modal Natural Language Generator (M-NLG)

Affective Reasoner (AR)

Page 10: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

NECA’s Architecture

Scene Generator

Text/Concept to Speech Synthesis (CTS)

User Input

Scene Description

Multi-modal Output

Multi-modal Natural Language Generator (M-NLG)

Phonetic+Prosodic Information

Affective Reasoner (AR)

Emotional Speech

Page 11: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

NECA’s Architecture

Scene Generator

Text/Concept to Speech Synthesis (CTS)

User Input

Scene Description

Multi-modal Output

Multi-modal Natural Language Generator (M-NLG)

Gesture Assignment Module (GA)

Phonetic+Prosodic Information

Affective Reasoner (AR)

Emotional Speech

Animation directives

Page 12: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

NECA’s Architecture

Scene Generator

Text/Concept to Speech Synthesis (CTS)

User Input

Scene Description

Multi-modal Output

Multi-modal Natural Language Generator (M-NLG)

Gesture Assignment Module (GA)

Animation Control Sequence

Phonetic+Prosodic Information

Affective Reasoner (AR)

Emotional Speech

Player-Specific Rendering

Animation directives

Page 13: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

NECA’s Architecture

Scene Generator

Text/Concept to Speech Synthesis (CTS)

User Input

Scene Description

Multi-modal Output

Multi-modal Natural Language Generator (M-NLG)

Gesture Assignment Module (GA)

Animation Control Sequence

Phonetic+Prosodic Information

Affective Reasoner (AR)

Emotional Speech

Player-Specific Rendering

Animation directives

RRL

RRL

RRL

RRL

Page 14: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Requirements for RRL

• Application Domain– Represent combinations of different types of

information– Expressivity

• Processing Modules– Ease of manipulation/search (incremental/fast)

• Developers (Maintainability)– Predictability– Locality– Conciseness– Intelligibility

Page 15: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Scene DescriptionSG

M-NLG

GA

TTS/CTS

What is a Scene? I Theatr. 1 A subdivision of (an act of) a play, in which the time is continuous and the setting fixed, …; the action and dialogue comprised in any one of these subdivisions. (New Shorter Oxford English Dictionary, 1996)

Page 16: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Scene Descriptions in a Nutshell

• Network representations:– Flat, uniform– Use the Description Logical T and A-box distinction.

T-box defines types, subtypes, attributes and constants

– Can emulate CFGs, so we can include, e.g., semantic representation languages: Discourse Representation Theory (Kamp & Reyle, 1994)

– Reification of expressions in the network provide useful handles for interleaving different types of information

– Lends itself well for graphical representation

Page 17: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Scene Descriptions in a Nutshell

• Further Features of (RRL) Scene Descriptions– For communication between modules: XML syntax– Temporal relations are explicitly represented.– Meta-conditions used in DRT for WH-questions,

Topics and Bridging Anaphora

Page 18: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

eShowRoom Example

Page 19: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

eShowRoom Example

Page 20: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

eShowRoom Example

Page 21: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

eShowRoom Example

Page 22: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Multimodal OutputSG

M-NLG

GA

TTS/CTS

• Multimodal Natural Language Generation (M-NLG) supplies– Information on emotional state– Conceptually rich input for Speech

Synthesis– Initial specification of gestures and facial

expressions for later use in Gesture Assignment

Page 23: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Neca’s Speech Synthesis: EmotionsSG

M-NLG

GA

TTS/CTS

• Not restricted to prosody (pitch, duration) • Several voice databases

– diphon-inventories for different voice qualities (modal, loud, soft)

• Emotive interjections• Gradual emotional states

– Shades of emotion / changing over time

Page 24: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Neca’s Speech Synthesis: Concept-to-SpeechSG

M-NLG

GA

TTS/CTS

• Concept-to-Speech instead of Text-to-Speech approach:– Part of Speech tags– Syntactic structure– Information status (given/new) – Information structure (theme/rheme)

Page 25: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

CTS specific informationSG

M-NLG

GA

TTS/CTS

• <sentence>• <text>This car has leather seats.</text>• <gesture modality="voice" meaning="beautiful"/>• <sentence>

Page 26: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

CTS specific informationSG

M-NLG

GA

TTS/CTS

• <sentence>• <text>This car has leather seats.</text>• <gesture modality="voice" meaning="beautiful"/>• • • <word text="This" pos="PDAT"/>• • <word text="car" pos="NN"/>• • • • • <word text="has" pos="VAFIN"/>• • <word text="leather seats" pos="NN" />• • <punct text="." pos="$."/>• </sentence>

Page 27: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

CTS specific informationSG

M-NLG

GA

TTS/CTS

• <sentence>• <text>This car has leather seats.</text>• <gesture modality="voice" meaning="beautiful"/>• • <synPhrase category="NP" function="SB">• <word text="This" pos="PDAT"/>• • <word text="car" pos="NN"/>• • </synPhrase>• • <synPhrase phrase="VP" function="PD"> • <word text="has" pos="VAFIN"/>• <synPhrase phrase="NP" function="OA">• <word text="leather seats" pos="NN" />• </synPhrase>• <punct text="." pos="$."/>• </synPhrase>•

Page 28: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

CTS specific informationSG

M-NLG

GA

TTS/CTS

• <sentence>• <text>This car has leather seats.</text>• <gesture modality="voice" meaning="beautiful"/>• • <synPhrase category="NP" function="SB">• <word text="This" pos="PDAT"/>• <infoStatus type="referent-given">• <word text="car" pos="NN"/>• <infoStatus />

• </synPhrase>• • <synPhrase phrase="VP" function="PD"> • <word text="has" pos="VAFIN"/>• <synPhrase phrase="NP" function="OA">• <word text="leather seats" pos="NN" />• </synPhrase>• <punct text="." pos="$."/>• </synPhrase>

Page 29: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

CTS specific informationSG

M-NLG

GA

TTS/CTS

• <sentence>• <text>This car has leather seats.</text>• <gesture modality="voice" meaning="beautiful"/>• <infoStruct part="theme">• <synPhrase category="NP" function="SB">• <word text="This" pos="PDAT"/>• <infoStatus type="referent-given">• <word text="car" pos="NN"/>• </infoStatus>• </synPhrase>• <infoStruct part="rheme">• <synPhrase phrase="VP" function="PD"> • <word text="has" pos="VAFIN"/>• <synPhrase phrase="NP" function="OA">• <word text="leather seats" pos="NN" />• </synPhrase>• <punct text="." pos="$."/>• </synPhrase>• </infoStruct>• </infoStruct>• </sentence>

Page 30: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Prosodic/Phonetic Information for GASG

M-NLG

GA

TTS/CTS

• Phonetics– exact timing of speech sounds,

pauses and interjections

• Prosody– boundarie locations for

• syllables• words• prosodic phrases

Page 31: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Prosodic/Phonetic Information for GASG

M-NLG

GA

TTS/CTS – information on:• syllables bearing word-stress• position and type of sentence accents• position and type of prosodic

boundaries

Page 32: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Animation directivesSG

M-NLG

GA

TTS/CTS • Phonetic information (phonemes) used for specifying

– Visemes– breathing

Page 33: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Animation directivesSG

M-NLG

GA

TTS/CTS • Prosodic information (stress, accents, phrasing) used for specifying – synchronization of gestures with speech– eye-blinking– gaze

Page 34: RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA Paul Piwek, ITRI, Brighton Brigitte Krenn, OFAI, Vienna Marc Schröder,

Conclusions

• RRL is representation language for wide range of expert knowledge required at interfaces of NECA modules.

• Scene Descriptions: uniform representation/integration of different types of information (illustrated with integration of DRT); using handles;…

• Speech Synthesis: conceptually rich input as opposed to text

• Gesture Assignment: access to exact timing of speech