Adversarial Training for Aspect-Based Sentiment Analysis with BERT

by   Akbar Karimi, et al.

Aspect-Based Sentiment Analysis (ABSA) deals with the extraction of sentiments and their targets. Collecting labeled data for this task in order to help neural networks generalize better can be laborious and time-consuming. As an alternative, similar data to the real-world examples can be produced artificially through an adversarial process which is carried out in the embedding space. Although these examples are not real sentences, they have been shown to act as a regularization method which can make neural networks more robust. In this work, we apply adversarial training, which was put forward by Goodfellow et al. (2014), to the post-trained BERT (BERT-PT) language model proposed by Xu et al. (2019) on the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis. After improving the results of post-trained BERT by an ablation study, we propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training in ABSA. The proposed model outperforms post-trained BERT in both tasks. To the best of our knowledge, this is the first study on the application of adversarial training in ABSA.


page 1

page 2

page 3

page 4


Improving BERT Performance for Aspect-Based Sentiment Analysis

Aspect-Based Sentiment Analysis (ABSA) studies the consumer opinion on t...

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

Question-answering plays an important role in e-commerce as it allows po...

A sentiment analysis model for car review texts based on adversarial training and whole word mask BERT

In the field of car evaluation, more and more netizens choose to express...

Adversarial Capsule Networks for Romanian Satire Detection and Sentiment Analysis

Satire detection and sentiment analysis are intensively explored natural...

A Visual Interpretation-Based Self-Improved Classification System Using Virtual Adversarial Training

The successful application of large pre-trained models such as BERT in n...

Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives

Over the past few years, adversarial training has become an extremely ac...

Transfer Learning Between Related Tasks Using Expected Label Proportions

Deep learning systems thrive on abundance of labeled training data but s...

Please sign up or login with your details

Forgot password? Click here to reset