Paper: Generating Recommendation Dialogs by Extracting Information from User Reviews

ACL ID P13-2089
Title Generating Recommendation Dialogs by Extracting Information from User Reviews
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

Recommendation dialog systems help users navigate e-commerce listings by ask- ing questions about users? preferences to- ward relevant domain attributes. We present a framework for generating and ranking fine-grained, highly relevant ques- tions from user-generated reviews. We demonstrate our approach on a new dataset just released by Yelp, and release a new sentiment lexicon with 1329 adjectives for the restaurant domain.