Informative and Controllable Opinion Summarization

TL;DR

This paper introduces a new opinion summarization framework that uses dense representations of reviews to generate more informative and customizable summaries, overcoming limitations of extractive methods.

Contribution

The proposed framework allows the use of all reviews without pre-selection and incorporates user preferences through zero-shot customization, improving summary informativeness.

Findings

Outperforms state-of-the-art on Rotten Tomatoes dataset

Enables effective user preference customization

Produces more informative summaries

Abstract

Opinion summarization is the task of automatically generating summaries for a set of reviews about a specific target (e.g., a movie or a product). Since the number of reviews for each target can be prohibitively large, neural network-based methods follow a two-stage approach where an extractive step first pre-selects a subset of salient opinions and an abstractive step creates the summary while conditioning on the extracted subset. However, the extractive model leads to loss of information which may be useful depending on user needs. In this paper we propose a summarization framework that eliminates the need to rely only on pre-selected content and waste possibly useful information, especially when customizing summaries. The framework enables the use of all input reviews by first condensing them into multiple dense vectors which serve as input to an abstractive model. We showcase an effective instantiation of our framework which produces more informative summaries and also allows to take user preferences into account using our zero-shot customization technique. Experimental results demonstrate that our model improves the state of the art on the Rotten Tomatoes dataset and generates customized summaries effectively.