Being as Informative as the User Wants: The Generation of Information Enriched Utterances.

@inproceedings{Ericsson2004BeingAI,
  title={Being as Informative as the User Wants: The Generation of Information Enriched Utterances.},
  author={Stina Ericsson},
  booktitle={FLAIRS Conference},
  year={2004}
}
The work in this paper is based on the claim that collaborative dialogue involves taking into account how much information an utterance conveys, in the sense that it thereby shows how it is connected to the linguistic and extra-linguistic context shared by speaker and hearer, by system and human user. I introduce a notion of information enrichment to handle this phenomenon, and discuss information enriched utterances in human-human dialogue and in the generation component of 

From This Paper

Figures, tables, and topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 13 references

Godis – qud-based dialogue management in a multi-domain dialogue system

S. Larsson, S. Ericsson
Technical abstract of demo, NAACL 2001. • 2001
View 1 Excerpt

Manual for trindikit 2.0

S. Larsson, A. Berman, +3 authors D. Traum
Deliverable D5.1, • 2000
View 1 Excerpt

Semantically-based ellipsis resolution with syntactic presuppositions

J. Ginzburg
Bunt, H., and Muskens, R., eds., Computing Meaning, volume 1. Kluwer. 255–279. • 1999
View 2 Excerpts

Interrogatives: Questions, facts and dialogue

J. Ginzburg
The Handbook of Contemporary Semantic Theory. Oxford: Blackwell. • 1996
View 2 Excerpts

The effect of resource limits and task complexity on collaborative planning in dialogue

M. A. Walker
Artificial Intelligence Journal 85(1-2). • 1996
View 1 Excerpt