Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

11-2019

Abstract

In this paper, we study abstractive review summarization. Observing that review summaries often consist of aspect words, opinion words and context words, we propose a two-stage reinforcement learning approach, which first predicts the output word type from the three types, and then leverages the predicted word type to generate the final word distribution. Experimental results on two Amazon product review datasets demonstrate that our method can consistently outperform several strong baseline approaches based on ROUGE scores.

Keywords

Natural Language Processing, Review Summarization, Text Generation, Neural Networks

Discipline

Computer and Systems Architecture | Digital Communications and Networking

Research Areas

Data Science and Engineering

Publication

Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, China, 2019 November 3-7

First Page

2061

Last Page

2064

Identifier

10.1145/3357384.3358142

City or Country

Beijing, China

Additional URL

https://doi.org/10.1145/3357384.3358142

Share

COinS