Computational Linguistics Colloquium
Monday, 28 June 2010, 14:15
Conference Room, Building C7 4
Please not the unusual date and time!
Learning semantics and pragmatics from dialogue historyMatthew Stone
We describe a methodology for learning a disambiguation model for deep pragmatic interpretations in the context of situated task-oriented dialogue. The system accumulates training examples for ambiguity resolution by tracking the fates of alternative interpretations across dialogue, including subsequent clarificatory episodes initiated by the system itself. We illustrate with a case study building maximum entropy models over abductive interpretations in a referential communication task. The resulting model correctly resolves 81% of ambiguities left unresolved by an initial handcrafted baseline. A key innovation is that our method draws exclusively on a system’s own skills and experience and requires no human annotation. (joint work with David DeVault, USC)
If you would like to meet with the speaker, please contact