{"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/document-level-relation-extraction-as","title":"Document-level Relation Extraction as Semantic Segmentation","arxiv_id":"2106.03618","date":"2021-06-07","proceeding":null,"authors":["Ningyu Zhang","Xiang Chen","Xin Xie","Shumin Deng","Chuanqi Tan","Mosha Chen","Fei Huang","Luo Si","Huajun Chen"],"abstract":"Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples. Experimental results show that our approach can obtain state-of-the-art performance on three benchmark datasets DocRED, CDR, and GDA.","url_abs":"https://arxiv.org/abs/2106.03618v2","url_pdf":"https://arxiv.org/pdf/2106.03618v2.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":"document-level-relation-extraction-as","repo_url":"https://github.com/zjunlp/DocuNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"document-level-relation-extraction-as","repo_url":"https://github.com/wutong8023/Awesome_Information_Extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"document-level-relation-extraction","task_name":"Document-level Relation Extraction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-cdr","task":"Relation Extraction","dataset":"CDR","model":"DocuNet-SciBERTbase","rank_in_archive_order":4,"of":10,"metrics":{"F1":"76.3"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"DocuNet-RoBERTa-large","rank_in_archive_order":6,"of":62,"metrics":{"F1":"64.55","Ign F1":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-gda","task":"Relation Extraction","dataset":"GDA","model":"DocuNet-SciBERTbase","rank_in_archive_order":4,"of":9,"metrics":{"F1":"85.3"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-redocred","task":"Relation Extraction","dataset":"ReDocRED","model":"DocuNET","rank_in_archive_order":6,"of":8,"metrics":{"F1":"77.87","Ign F1":"77.26"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.03618","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}