Comparative Opinion Summarization via Collaborative Decoding

TL;DR

This paper introduces a new task and framework for generating comparative summaries from reviews, enabling better comparison of options, and demonstrates its effectiveness on a new benchmark dataset.

Contribution

The paper proposes the comparative opinion summarization task and the CoCoSum framework, which jointly generates contrastive and common summaries from review sets.

Findings

CoCoSum outperforms existing opinion summarization models on the CoCoTrip benchmark.

The framework effectively produces contrastive and common summaries that aid comparison.

Experimental results validate the quality and usefulness of the generated summaries.

Abstract

Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and concise information about a particular hotel or product, the information may be insufficient to help the user compare multiple different choices. Thus, the user may still struggle with the question "Which one should I pick?" In this paper, we propose the comparative opinion summarization task, which aims at generating two contrastive summaries and one common summary from two different candidate sets of reviews. We develop a comparative summarization framework CoCoSum, which consists of two base summarization models that jointly generate contrastive and common summaries. Experimental results on a newly created benchmark CoCoTrip show that CoCoSum can produce higher-quality contrastive and common summaries than state-of-the-art opinion summarization models. The dataset and code are available at https://github.com/megagonlabs/cocosum