An Enhanced MeanSum Method For Generating Hotel Multi-Review Summarizations

TL;DR

This paper enhances the MeanSum method for multi-review hotel summarization by incorporating a multi-aspect content selector and length regularizer, resulting in improved ROUGE and sentiment accuracy on Trip Advisor data.

Contribution

It introduces Multi-Aspect Masker for better content selection and a length control regularizer, advancing unsupervised abstractive summarization for multi-review data.

Findings

Higher ROUGE scores than original Meansum

Improved sentiment accuracy

Comparable performance to supervised methods

Abstract

Multi-document summaritazion is the process of taking multiple texts as input and producing a short summary text based on the content of input texts. Up until recently, multi-document summarizers are mostly supervised extractive. However, supervised methods require datasets of large, paired document-summary examples which are rare and expensive to produce. In 2018, an unsupervised multi-document abstractive summarization method(Meansum) was proposed by Chu and Liu, and demonstrated competitive performances comparing to extractive methods. Despite good evaluation results on automatic metrics, Meansum has multiple limitations, notably the inability of dealing with multiple aspects. The aim of this work was to use Multi-Aspect Masker(MAM) as content selector to address the issue with multi-aspect. Moreover, we propose a regularizer to control the length of the generated summaries. Through a series of experiments on the hotel dataset from Trip Advisor, we validate our assumption and show that our improved model achieves higher ROUGE, Sentiment Accuracy than the original Meansum method and also beats/ comprarable/close to the supervised baseline.