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

NAACL 2019  ·  Hu Xu, Bing Liu, Lei Shu, Philip S. Yu ·

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

PDF Abstract NAACL 2019 PDF NAACL 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Sub Task 1 BERT-PT Laptop (F1) 84.26 # 2
Restaurant (F1) 77.97 # 2
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Sub Task 2 BERT-PT Restaurant (Acc) 84.95 # 12
Laptop (Acc) 78.07 # 14
Mean Acc (Restaurant + Laptop) 81.51 # 14