Rationale-based Opinion Summarization

Anonymous

TL;DR: We propose rationale-based opinion summarization which presents represenative opinions as well as their rationales.

Abstract:

Opinion summarization aims to generate concise summaries that present popular opinions of a large group of reviews. However, these
summaries can be too generic and lack supporting details. To address these issues, we propose a new paradigm for summarizing reviews, rationale-based opinion summarization. Rationale-based opinion summaries outputs the representative opinions as well as one or more corresponding rationales. To extract good rationales, we define four desirable properties: relatedness, specificity, popularity, and diversity and present a Gibbs-sampling-based method to extract rationales. Overall, we propose RATION, an unsupervised extractive system that has two components: an Opinion Extractor (to extract representative opinions) and Rationales Extractor (to extract corresponding rationales). We conduct automatic and human evaluations to show that rationales extracted by RATION have the proposed properties and its %the rationale-based summaries are more useful than conventional summaries.

Paper Type: long

Research Area: Summarization

Contribution Types: NLP engineering experiment

Languages Studied: English