Utilizing Review Summarization in a Spoken Recommendation System

Jingjing Liu,  Stephanie Seneff,  Victor Zue


In this paper we present a framework for spoken recommendation systems. To provide reliable recommendations to users, we incorporate a review summarization technique which harvests reviews from grassroots users to extract informative opinion summaries. The dialogue system then utilizes these review summaries to support both quality-based opinion inquiry and feature-specific entity search. To generate recommendations in spoken language from the text-based opinion summaries, we propose a probabilistic language generation approach to automatically creating natural responses based on linguistic parsing statistics. A user study in the restaurant domain shows that the proposed approaches can effectively generate reliable recommendations in human-computer conversations, and our prototype dialogue system is considered to be very helpful by general users.