Aspect-Controllable Opinion Summarization

TL;DR

This paper introduces a method for generating personalized opinion summaries based on specific aspect queries, using synthetic training data and aspect controllers to produce customized, aspect-specific summaries.

Contribution

It presents a novel approach that enables aspect-controllable opinion summarization by leveraging synthetic datasets and multi-level aspect prediction.

Findings

Outperforms previous state-of-the-art models on benchmark datasets.

Generates personalized summaries by controlling aspect inclusion.

Uses synthetic data and aspect controllers for fine-tuning.

Abstract

Recent work on opinion summarization produces general summaries based on a set of input reviews and the popularity of opinions expressed in them. In this paper, we propose an approach that allows the generation of customized summaries based on aspect queries (e.g., describing the location and room of a hotel). Using a review corpus, we create a synthetic training dataset of (review, summary) pairs enriched with aspect controllers which are induced by a multi-instance learning model that predicts the aspects of a document at different levels of granularity. We fine-tune a pretrained model using our synthetic dataset and generate aspect-specific summaries by modifying the aspect controllers. Experiments on two benchmarks show that our model outperforms the previous state of the art and generates personalized summaries by controlling the number of aspects discussed in them.