Multimodal Meaning Representation for Generic Dialogue Systems Architectures
Identifieur interne : 006D05 ( Main/Merge ); précédent : 006D04; suivant : 006D06Multimodal Meaning Representation for Generic Dialogue Systems Architectures
Auteurs : Frédéric Landragin ; Alexandre Denis ; Annalisa Ricci ; Laurent RomarySource :
English descriptors
Abstract
An unified language for the communicative acts between agents is essential for the design of multi-agents architectures. Whatever the type of interaction (linguistic, multimodal, including particular aspects such as force feedback), whatever the type of application (command dialogue, request dialogue, database querying), the concepts are common and we need a generic meta-model. In order to tend towards task-independent systems, we need to clarify the modules parameterization procedures. In this paper, we focus on the characteristics of a meta-model designed to represent meaning in linguistic and multimodal applications. This meta-model is called MMIL for MultiModal Interface Language, and has first been specified in the framework of the IST MIAMM European project. What we want to test here is how relevant is MMIL for a completely different context (a different task, a different interaction type, a different linguistic domain). We detail the exploitation of MMIL in the framework of the IST OZONE European project, and we draw the conclusions on the role of MMIL in the parameterization of task-independent dialogue managers.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003D36
- to stream Crin, to step Curation: 003D36
- to stream Crin, to step Checkpoint: 000830
Links to Exploration step
CRIN:landragin04cLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="187">Multimodal Meaning Representation for Generic Dialogue Systems Architectures</title></titleStmt><publicationStmt><idno type="RBID">CRIN:landragin04c</idno><date when="2004" year="2004">2004</date><idno type="wicri:Area/Crin/Corpus">003D36</idno><idno type="wicri:Area/Crin/Curation">003D36</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003D36</idno><idno type="wicri:Area/Crin/Checkpoint">000830</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">000830</idno><idno type="wicri:Area/Main/Merge">006D05</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Multimodal Meaning Representation for Generic Dialogue Systems Architectures</title><author><name sortKey="Landragin, Frederic" sort="Landragin, Frederic" uniqKey="Landragin F" first="Frédéric" last="Landragin">Frédéric Landragin</name></author><author><name sortKey="Denis, Alexandre" sort="Denis, Alexandre" uniqKey="Denis A" first="Alexandre" last="Denis">Alexandre Denis</name></author><author><name sortKey="Ricci, Annalisa" sort="Ricci, Annalisa" uniqKey="Ricci A" first="Annalisa" last="Ricci">Annalisa Ricci</name></author><author><name sortKey="Romary, Laurent" sort="Romary, Laurent" uniqKey="Romary L" first="Laurent" last="Romary">Laurent Romary</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>exchanges between agents</term><term>multimodality</term><term>normalization</term><term>semantic representation</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="3104">An unified language for the communicative acts between agents is essential for the design of multi-agents architectures. Whatever the type of interaction (linguistic, multimodal, including particular aspects such as force feedback), whatever the type of application (command dialogue, request dialogue, database querying), the concepts are common and we need a generic meta-model. In order to tend towards task-independent systems, we need to clarify the modules parameterization procedures. In this paper, we focus on the characteristics of a meta-model designed to represent meaning in linguistic and multimodal applications. This meta-model is called MMIL for MultiModal Interface Language, and has first been specified in the framework of the IST MIAMM European project. What we want to test here is how relevant is MMIL for a completely different context (a different task, a different interaction type, a different linguistic domain). We detail the exploitation of MMIL in the framework of the IST OZONE European project, and we draw the conclusions on the role of MMIL in the parameterization of task-independent dialogue managers.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 006D05 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 006D05 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Merge
|type= RBID
|clé= CRIN:landragin04c
|texte= Multimodal Meaning Representation for Generic Dialogue Systems Architectures
}}
| This area was generated with Dilib version V0.6.33. |  |