Generating Referring Expressions in Multimodal Contexts

Susanne Salmon-Alt 1 Laurent Romary 1
1 LANGUE ET DIALOGUE - Human-machine dialogue with a significant language component
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper adresses the need of structuring the global context set into subsets or domains in order to explain adequately the use of referring expressions in a multimodal corpus. We underline, in particular, the importance of taking into account not only the discourse, but also perception and gestures for the construction of these domains. We propose a unified context model where the context is built up dynamically from different information sources and show that this way of context modelling predicts correctly the use of referring expressions in a corpus of instructional dialogues.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00323339
Contributor : Laurent Romary <>
Submitted on : Saturday, September 20, 2008 - 4:46:26 PM
Last modification on : Friday, March 22, 2019 - 2:22:12 PM
Document(s) archivé(s) le : Friday, June 4, 2010 - 11:38:11 AM

File

alt-final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00323339, version 1

Collections

Citation

Susanne Salmon-Alt, Laurent Romary. Generating Referring Expressions in Multimodal Contexts. International Natural Language Generation Conference, Jun 2000, Mitzpe Ramon, Israel. ⟨hal-00323339⟩

Share

Metrics

Record views

208

Files downloads

80