GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis
This addresses a specific problem in natural language processing for sentiment analysis, but it is incremental as it builds on existing methods.
The paper tackles the imbalance issue and lack of interaction between aspect terms in aspect-based sentiment analysis by proposing GRACE, which achieves state-of-the-art results on multiple benchmark datasets.
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.