{"url":"/sota/relation-extraction-on-redocred","task":{"name":"Relation Extraction","url":"/task/relation-extraction","note":null},"dataset":{"name":"ReDocRED","url":"/dataset/re-docred"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Relation Extraction** is the task of predicting attributes and relations for entities in a sentence. For example, given a sentence “Barack Obama was born in Honolulu, Hawaii.”, a relation classifier aims at predicting the relation of “bornInCity”. Relation Extraction is the key component for building relation knowledge graphs, and it is of crucial significance to natural language processing applications such as structured search, sentiment analysis, question answering, and summarization.\r\n\r\n\r\n<span class=\"description-source\">Source: [Deep Residual Learning for Weakly-Supervised Relation Extraction ](https://arxiv.org/abs/1707.08866)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1","Ign F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher","Ign F1":"higher"}},"counts":{"rows":8,"rows_with_code":8,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"TTM-RE","metrics":{"F1":"84.01","Ign F1":"83.11"},"uses_additional_data":true,"paper_date":"2024-06-09","paper":"/paper/ttm-re-memory-augmented-document-level","paper_url":"https://arxiv.org/abs/2406.05906v1","paper_title":"TTM-RE: Memory-Augmented Document-Level Relation Extraction","code":"https://github.com/chufangao/ttm-re","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"DREEAM","metrics":{"F1":"80.73","Ign F1":"79.66"},"uses_additional_data":false,"paper_date":"2023-02-17","paper":"/paper/dreeam-guiding-attention-with-evidence-for","paper_url":"https://arxiv.org/abs/2302.08675v1","paper_title":"DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction","code":"https://github.com/youmima/dreeam","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"HingeABL","metrics":{"F1":"79.79","Ign F1":"78.82"},"uses_additional_data":false,"paper_date":"2023-12-06","paper":"/paper/adaptive-hinge-balance-loss-for-document","paper_url":"https://aclanthology.org/2023.findings-emnlp.253/","paper_title":"Adaptive Hinge Balance Loss for Document-Level Relation Extraction","code":"https://github.com/Jize-W/HingeABL","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"SSR-PU","metrics":{"F1":"78.86","Ign F1":"77.67"},"uses_additional_data":false,"paper_date":"2022-10-17","paper":"/paper/a-unified-positive-unlabeled-learning","paper_url":"https://arxiv.org/abs/2210.08709v2","paper_title":"A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling","code":"https://github.com/www-ye/ssr-pu","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"KD-DocRE","metrics":{"F1":"78.28","Ign F1":"77.60"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/document-level-relation-extraction-with-4","paper_url":"https://arxiv.org/abs/2203.10900v1","paper_title":"Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation","code":"https://github.com/tonytan48/kd-docre","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DocuNET","metrics":{"F1":"77.87","Ign F1":"77.26"},"uses_additional_data":false,"paper_date":"2021-06-07","paper":"/paper/document-level-relation-extraction-as","paper_url":"https://arxiv.org/abs/2106.03618v2","paper_title":"Document-level Relation Extraction as Semantic Segmentation","code":"https://github.com/zjunlp/DocuNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"ATLOP","metrics":{"F1":"77.56","Ign F1":"76.82"},"uses_additional_data":false,"paper_date":"2020-10-21","paper":"/paper/document-level-relation-extraction-with","paper_url":"https://arxiv.org/abs/2010.11304v3","paper_title":"Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling","code":"https://github.com/wzhouad/ATLOP","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":8,"model":"JEREX","metrics":{"F1":"72.57","Ign F1":"71.45"},"uses_additional_data":false,"paper_date":"2021-02-11","paper":"/paper/an-end-to-end-model-for-entity-level-relation","paper_url":"https://arxiv.org/abs/2102.05980v2","paper_title":"An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning","code":"https://github.com/lavis-nlp/jerex","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}