Natural Language Generation and Discourse Context: Computing Distractor Sets from the Focus Stack
DeVault, D.; Rich, C.; Sidner, C.L., “Natural Language Generation and Discourse Context: Computing Distractor Sets from the Focus Stack”, International Florida Artificial Intelligence Research Symposium (FLAIRS), May 2004 (FLAIRS 2004)
|MERL Report: ||TR2004-004: DeVault, D.; Rich, C.; Sidner, C.L.
In human-human conversation, people use linguistic expressions that are flexible tailored to context as a matter of course, and they expect their conversational partners to do likewise. Towards our goal of helping computers achieve natural linguistic interactions with human uses, we have developed an applicaiton-independent dialogue system integrating the COLLAGEN collaboration manager with the SPUD natural language generation algorithm. In this paper, we show how this integration supports investigation into strategies for distractor set baased generation in dialogue. We discuss, as a case study, our experience in using the integrated system to generate contextually appropriate noun phrases in an email and scheduling applicaiton. While we have achieved natural, context-sensitive output in certain cases, our work has also revaealed serval issues facing systems wishing to expooit distractor sets to tun-tune their linguistic output. We discuss our approach to handling these issues and suggest areaas where further research is required.