{"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/graph-refinement-for-coreference-resolution-1","title":"Graph Refinement for Coreference Resolution","arxiv_id":"2203.16574","date":"2022-03-30","proceeding":"Findings (ACL) 2022 5","authors":["Lesly Miculicich","James Henderson"],"abstract":"The state-of-the-art models for coreference resolution are based on independent mention pair-wise decisions. We propose a modelling approach that learns coreference at the document-level and takes global decisions. For this purpose, we model coreference links in a graph structure where the nodes are tokens in the text, and the edges represent the relationship between them. Our model predicts the graph in a non-autoregressive manner, then iteratively refines it based on previous predictions, allowing global dependencies between decisions. The experimental results show improvements over various baselines, reinforcing the hypothesis that document-level information improves conference resolution.","url_abs":"https://arxiv.org/abs/2203.16574v1","url_pdf":"https://arxiv.org/pdf/2203.16574v1.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":"graph-refinement-for-coreference-resolution-1","repo_url":"https://github.com/idiap/g2g-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/coreference-resolution-on-ontonotes","task":"Coreference Resolution","dataset":"OntoNotes","model":"G2GT SpanBERT-large reduced","rank_in_archive_order":9,"of":26,"metrics":{"F1":"80.5"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-ontonotes","task":"Coreference Resolution","dataset":"OntoNotes","model":"G2GT SpanBERT-large overlap","rank_in_archive_order":10,"of":26,"metrics":{"F1":"80.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.16574","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}