Paper: Learning to Interpret Utterances Using Dialogue History

ACL ID E09-1022
Title Learning to Interpret Utterances Using Dialogue History
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2009

We describe a methodology for learning a disambiguation model for deep pragmatic interpretations in the context of situated task-oriented dialogue. The system accu- mulates training examples for ambiguity resolution by tracking the fates of alter- native interpretations across dialogue, in- cluding subsequent clarificatory episodes initiated by the system itself. We illus- trate with a case study building maxi- mum entropy models over abductive in- terpretations in a referential communica- tiontask. Theresultingmodelcorrectlyre- solves 81% of ambiguities left unresolved by an initial handcrafted baseline. A key innovation is that our method draws exclu- sively on a system’s own skills and experi- ence and requires no human annotation.