An Enhanced MeanSum Method For Generating Hotel Multi-Review Summarizations
This work provides an incremental improvement for unsupervised multi-document abstractive summarization, particularly beneficial for generating more nuanced and accurate summaries of hotel reviews for potential travelers or businesses.
This paper enhances the MeanSum method for multi-document abstractive summarization, specifically for hotel reviews. The improved model, using a Multi-Aspect Masker and a length regularizer, achieves higher ROUGE and Sentiment Accuracy compared to the original MeanSum and performs comparably to supervised baselines on the Trip Advisor hotel dataset.
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.