BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis

TL;DR

This paper introduces ReviewRC, a new dataset for review reading comprehension, and proposes a novel BERT post-training method that significantly improves performance on review-based NLP tasks.

Contribution

The paper presents the first ReviewRC dataset for review reading comprehension and a novel BERT post-training approach to enhance performance on review-related tasks.

Findings

Post-training BERT improves RRC performance

Effective for aspect-based sentiment analysis tasks

Significantly boosts review question-answering accuracy

Abstract

Question-answering plays an important role in e-commerce as it allows potential customers to actively seek crucial information about products or services to help their purchase decision making. Inspired by the recent success of machine reading comprehension (MRC) on formal documents, this paper explores the potential of turning customer reviews into a large source of knowledge that can be exploited to answer user questions.~We call this problem Review Reading Comprehension (RRC). To the best of our knowledge, no existing work has been done on RRC. In this work, we first build an RRC dataset called ReviewRC based on a popular benchmark for aspect-based sentiment analysis. Since ReviewRC has limited training examples for RRC (and also for aspect-based sentiment analysis), we then explore a novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC. To show the generality of the approach, the proposed post-training is also applied to some other review-based tasks such as aspect extraction and aspect sentiment classification in aspect-based sentiment analysis. Experimental results demonstrate that the proposed post-training is highly effective. The datasets and code are available at https://www.cs.uic.edu/~hxu/.