GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis

In this paper, we focus on the imbalance issue, which is rarely studied in aspect term extraction and aspect sentiment classification when regarding them as sequence labeling tasks. Besides, previous works usually ignore the interaction between aspect terms when labeling polarities. We propose a GRadient hArmonized and CascadEd labeling model (GRACE) to solve these problems. Specifically, a cascaded labeling module is developed to enhance the interchange between aspect terms and improve the attention of sentiment tokens when labeling sentiment polarities. The polarities sequence is designed to depend on the generated aspect terms labels. To alleviate the imbalance issue, we extend the gradient harmonized mechanism used in object detection to the aspect-based sentiment analysis by adjusting the weight of each label dynamically. The proposed GRACE adopts a post-pretraining BERT as its backbone. Experimental results demonstrate that the proposed model achieves consistency improvement on multiple benchmark datasets and generates state-of-the-art results.

PDF Abstract Findings of 2020 PDF Findings of 2020 Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Subtask 1+2 GRACE F1 70.71 # 1
Sentiment Analysis SemEval 2014 Task 4 Subtask 1+2 GRACE F1 70.71 # 1

Methods