Disambiguating Between Generic and Referential "You" in Dialog

We describe an algorithm for a novel task: disambiguating the pronoun you in conversation. You can be generic or referential; finding referential you is important for tasks such as addressee identification or extracting ‘owners’ of action items. Our classifier achieves 84% accuracy in two-person conversations; an initial study shows promising performance even on more complex multi-party meetings.

• Type: Conference
• Year: 2007
• Where: ACL
• Authors: Surabhi Gupta, Matthew Purver, Daniel Jurafsky
• Keywords: ACL 2007, Complex Multi-party Meetings, Computational Linguistics, Referential, Two-person Conversations