{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/grace-gradient-harmonized-and-cascaded","title":"GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis","arxiv_id":"2009.10557","date":"2020-09-22","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Huaishao Luo","Lei Ji","Tianrui Li","Nan Duan","Daxin Jiang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2009.10557v2","url_pdf":"https://arxiv.org/pdf/2009.10557v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"grace-gradient-harmonized-and-cascaded","repo_url":"https://github.com/ArrowLuo/GRACE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis-1","task_name":"Aspect-Based Sentiment Analysis"},{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"term-extraction","task_name":"Term Extraction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-on-semeval-6","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"SemEval 2014 Task 4 Subtask 1+2","model":"GRACE","rank_in_archive_order":4,"of":10,"metrics":{"F1":"70.71"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-semeval-2014-task-4","task":"Sentiment Analysis","dataset":"SemEval 2014 Task 4 Subtask 1+2","model":"GRACE","rank_in_archive_order":2,"of":8,"metrics":{"F1":"70.71"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.10557","atlas_url":"https://app.syntology.ai/?focus=2009.10557","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}