Abstractive summarization of product reviews using discourse structure

Abstract

We propose a novel abstractive summarization system for product reviews by taking advantage of their discourse structure. First, we apply a discourse parser to each review and obtain a discourse tree representation for every review. We then modify the discourse trees such that every leaf node only contains the aspect words. Second, we aggregate the aspect discourse trees and generate a graph. We then select a subgraph representing the most important aspects and the rhetorical relations between them using a PageRank algorithm, and transform the selected subgraph into an aspect tree. Finally, we generate a natural language summary by applying a template-based NLG framework. Quantitative and qualitative analysis of the results, based on two user studies, show that our approach significantly outperforms extractive and abstractive baselines.