{"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/double-graph-based-reasoning-for-document","title":"Double Graph Based Reasoning for Document-level Relation Extraction","arxiv_id":"2009.13752","date":"2020-09-29","proceeding":"EMNLP 2020 11","authors":["Shuang Zeng","Runxin Xu","Baobao Chang","Lei LI"],"abstract":"Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN) featuring double graphs. GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document. It also constructs an entity-level graph (EG), based on which we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at https://github.com/DreamInvoker/GAIN .","url_abs":"https://arxiv.org/abs/2009.13752v1","url_pdf":"https://arxiv.org/pdf/2009.13752v1.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":"double-graph-based-reasoning-for-document","repo_url":"https://github.com/DreamInvoker/GAIN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"double-graph-based-reasoning-for-document","repo_url":"https://github.com/pkunlp-icler/gain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","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":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"GAIN-BERT-large","rank_in_archive_order":12,"of":62,"metrics":{"F1":"62.76","Ign F1":"60.31"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"GAIN-BERT","rank_in_archive_order":27,"of":62,"metrics":{"F1":"61.24","Ign F1":"59.00"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"GAIN-GloVe","rank_in_archive_order":53,"of":62,"metrics":{"F1":"55.08","Ign F1":"52.66"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.13752","atlas_url":"https://app.syntology.ai/?focus=2009.13752","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}