{"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/coarse-to-fine-entity-representations-for","title":"Coarse-to-Fine Entity Representations for Document-level Relation Extraction","arxiv_id":"2012.02507","date":"2020-12-04","proceeding":null,"authors":["Damai Dai","Jing Ren","Shuang Zeng","Baobao Chang","Zhifang Sui"],"abstract":"Document-level Relation Extraction (RE) requires extracting relations expressed within and across sentences. Recent works show that graph-based methods, usually constructing a document-level graph that captures document-aware interactions, can obtain useful entity representations thus helping tackle document-level RE. These methods either focus more on the entire graph, or pay more attention to a part of the graph, e.g., paths between the target entity pair. However, we find that document-level RE may benefit from focusing on both of them simultaneously. Therefore, to obtain more comprehensive entity representations, we propose the Coarse-to-Fine Entity Representation model (CFER) that adopts a coarse-to-fine strategy involving two phases. First, CFER uses graph neural networks to integrate global information in the entire graph at a coarse level. Next, CFER utilizes the global information as a guidance to selectively aggregate path information between the target entity pair at a fine level. In classification, we combine the entity representations from both two levels into more comprehensive representations for relation extraction. Experimental results on two document-level RE datasets, DocRED and CDR, show that CFER outperforms existing models and is robust to the uneven label distribution.","url_abs":"https://arxiv.org/abs/2012.02507v2","url_pdf":"https://arxiv.org/pdf/2012.02507v2.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":"coarse-to-fine-entity-representations-for","repo_url":"https://github.com/Hunter-DDM/cfer-document-level-RE","is_official":1,"mentioned_in_paper":1,"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"CFER-BERT-base","rank_in_archive_order":34,"of":62,"metrics":{"F1":"59.82","Ign F1":"57.89"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"CFER-GloVe","rank_in_archive_order":50,"of":62,"metrics":{"F1":"55.75","Ign F1":"53.43"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2012.02507","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}