{"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/few-shot-document-level-relation-extraction","title":"Few-Shot Document-Level Relation Extraction","arxiv_id":"2205.02048","date":"2022-05-04","proceeding":"NAACL 2022 7","authors":["Nicholas Popovic","Michael Färber"],"abstract":"We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark. As opposed to existing benchmarks which are built on sentence-level relation extraction corpora, we argue that document-level corpora provide more realism, particularly regarding none-of-the-above (NOTA) distributions. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. We adapt the state-of-the-art sentence-level method MNAV to the document-level and develop it further for improved domain adaptation. We find FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set. The data, code, and trained models are available online (https://github.com/nicpopovic/FREDo).","url_abs":"https://arxiv.org/abs/2205.02048v2","url_pdf":"https://arxiv.org/pdf/2205.02048v2.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":"few-shot-document-level-relation-extraction","repo_url":"https://github.com/nicpopovic/fredo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"document-level-relation-extraction","task_name":"Document-level Relation Extraction"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-relation-classification","task_name":"Few-Shot Relation Classification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"fredo","name":"FREDo","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-relation-classification-on-docred","task":"Few-Shot Relation Classification","dataset":"DocRED","model":"DL-MNAV","rank_in_archive_order":1,"of":1,"metrics":{"F1 (1-Doc)":"7.05","F1 (3-Doc)":"8.42"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-relation-classification-on-fredo","task":"Few-Shot Relation Classification","dataset":"FREDo","model":"DL-MNAV","rank_in_archive_order":1,"of":1,"metrics":{"F1 (1-Doc)":"7.05","F1 (3-Doc)":"8.42"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-relation-classification-on-fredo-1","task":"Few-Shot Relation Classification","dataset":"FREDo (cross-domain)","model":"DL-MNAV+SIE+SBN","rank_in_archive_order":1,"of":1,"metrics":{"F1 (1-Doc)":"2.85","F1 (3-Doc)":"3.72"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-relation-classification-on-scierc","task":"Few-Shot Relation Classification","dataset":"SciERC","model":"DL-MNAV+SIE+SBN","rank_in_archive_order":1,"of":1,"metrics":{"F1 (1-Doc)":"2.85","F1 (3-Doc)":"3.72"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.02048","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}