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

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

22 Sep 2020Findings of the Association for Computational Linguistics 2020arXiv:2009.10557archive 2025-07-28

Huaishao Luo, Lei Ji, Tianrui Li, Nan Duan, Daxin Jiang

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.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ArrowLuo/GRACE officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)Object Detection Sentiment Analysis Sentiment Classification Term Extraction object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Aspect-Based Sentiment Analysis (ABSA)	SemEval 2014 Task 4 Subtask 1+2	GRACE	F1	70.71	#4 of 10	Archive leaderboard	report
Sentiment Analysis	SemEval 2014 Task 4 Subtask 1+2	GRACE	F1	70.71	#2 of 8	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections