{"url":"/sota/relation-extraction-on-tacred","task":{"name":"Relation Extraction","url":"/task/relation-extraction","note":null},"dataset":{"name":"TACRED","url":"/dataset/tacred"},"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","F1 (10% Few-Shot)","F1 (5% Few-Shot)","F1 (1% Few-Shot)","F1 (Zero-Shot)"],"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","F1 (10% Few-Shot)":"higher","F1 (5% Few-Shot)":"higher","F1 (1% Few-Shot)":"higher","F1 (Zero-Shot)":"higher"}},"counts":{"rows":40,"rows_with_code":35,"rows_with_paper_page":40,"rows_dated":40,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"RAG4RE","metrics":{"F1":"86.6"},"uses_additional_data":false,"paper_date":"2024-04-20","paper":"/paper/retrieval-augmented-generation-based-relation","paper_url":"https://arxiv.org/abs/2404.13397v1","paper_title":"Retrieval-Augmented Generation-based Relation Extraction","code":"https://github.com/sefeoglu/rag4re","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DeepStruct multi-task w/ finetune","metrics":{"F1":"76.8"},"uses_additional_data":false,"paper_date":"2022-05-21","paper":"/paper/deepstruct-pretraining-of-language-models-for-1","paper_url":"https://arxiv.org/abs/2205.10475v2","paper_title":"DeepStruct: Pretraining of Language Models for Structure Prediction","code":"https://github.com/cgraywang/deepstruct","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":6,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"UNiST (LARGE)","metrics":{"F1":"75.5"},"uses_additional_data":false,"paper_date":"2022-05-04","paper":"/paper/unified-semantic-typing-with-meaningful-label","paper_url":"https://arxiv.org/abs/2205.01826v1","paper_title":"Unified Semantic Typing with Meaningful Label Inference","code":"https://github.com/luka-group/unist","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"RE-MC","metrics":{"F1":"75.4"},"uses_additional_data":true,"paper_date":"2022-06-29","paper":"/paper/enhancing-targeted-minority-class-prediction","paper_url":"https://www.mdpi.com/1424-8220/22/13/4911","paper_title":"Enhancing Targeted Minority Class Prediction in Sentence-Level Relation Extraction","code":"https://github.com/henry-paik/EnhancingREMC","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"GenPT (T5)","metrics":{"F1":"75.3"},"uses_additional_data":false,"paper_date":"2022-10-22","paper":"/paper/generative-prompt-tuning-for-relation-1","paper_url":"https://arxiv.org/abs/2210.12435v1","paper_title":"Generative Prompt Tuning for Relation Classification","code":"https://github.com/hanjiale/genpt","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"RECENT+SpanBERT","metrics":{"F1":"75.2"},"uses_additional_data":false,"paper_date":"2021-05-18","paper":"/paper/relation-classification-with-entity-type","paper_url":"https://arxiv.org/abs/2105.08393v1","paper_title":"Relation Classification with Entity Type Restriction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"SuRE (PEGASUS-large)","metrics":{"F1":"75.1","F1 (1% Few-Shot)":"52","F1 (10% Few-Shot)":"70.7","F1 (5% Few-Shot)":"64.9","F1 (Zero-Shot)":"20.6"},"uses_additional_data":false,"paper_date":"2022-05-19","paper":"/paper/summarization-as-indirect-supervision-for","paper_url":"https://arxiv.org/abs/2205.09837v2","paper_title":"Summarization as Indirect Supervision for Relation Extraction","code":"https://github.com/luka-group/sure","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"EXOBRAIN","metrics":{"F1":"75.0"},"uses_additional_data":false,"paper_date":"2021-07-20","paper":"/paper/improving-sentence-level-relation-extraction","paper_url":"https://arxiv.org/abs/2107.09332v2","paper_title":"Improving Sentence-Level Relation Extraction through Curriculum Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Relation Reduction","metrics":{"F1":"74.8"},"uses_additional_data":false,"paper_date":"2020-10-09","paper":"/paper/relation-extraction-as-two-way-span","paper_url":"https://arxiv.org/abs/2010.04829v2","paper_title":"Relation Classification as Two-way Span-Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"RoBERTa-large-typed-marker","metrics":{"F1":"74.6"},"uses_additional_data":false,"paper_date":"2021-02-02","paper":"/paper/an-improved-baseline-for-sentence-level","paper_url":"https://arxiv.org/abs/2102.01373v4","paper_title":"An Improved Baseline for Sentence-level Relation Extraction","code":"https://github.com/wzhouad/RE_improved_baseline","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"NLI_DeBERTa","metrics":{"F1":"73.9","F1 (1% Few-Shot)":"63.7","F1 (10% Few-Shot)":"67.9","F1 (5% Few-Shot)":"69.0","F1 (Zero-Shot)":"62.8"},"uses_additional_data":false,"paper_date":"2021-09-08","paper":"/paper/label-verbalization-and-entailment-for","paper_url":"https://arxiv.org/abs/2109.03659v1","paper_title":"Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction","code":"https://github.com/osainz59/Ask2Transformers","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Noise-robust Co-regularization + BERT-large","metrics":{"F1":"73.0"},"uses_additional_data":false,"paper_date":"2021-04-17","paper":"/paper/learning-from-noisy-labels-for-entity-centric","paper_url":"https://arxiv.org/abs/2104.08656v2","paper_title":"Learning from Noisy Labels for Entity-Centric Information Extraction","code":"https://github.com/wzhouad/NLL-IE","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"DeNERT-KG","metrics":{"F1":"72.4"},"uses_additional_data":true,"paper_date":"2020-09-15","paper":"/paper/denert-kg-named-entity-and-relation","paper_url":"https://www.mdpi.com/2076-3417/10/18/6429/htm","paper_title":"DeNERT-KG: Named Entity and Relation Extraction Model Using DQN, Knowledge Graph, and BERT","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"K-ADAPTER (F+L)","metrics":{"F1":"72.04","F1 (1% Few-Shot)":"13.8","F1 (10% Few-Shot)":"56.0","F1 (5% Few-Shot)":"45.1"},"uses_additional_data":true,"paper_date":"2020-02-05","paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","paper_url":"https://arxiv.org/abs/2002.01808v5","paper_title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","code":"https://github.com/microsoft/K-Adapter","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"TANL","metrics":{"F1":"71.9"},"uses_additional_data":false,"paper_date":"2021-01-14","paper":"/paper/structured-prediction-as-translation-between-1","paper_url":"https://arxiv.org/abs/2101.05779v3","paper_title":"Structured Prediction as Translation between Augmented Natural Languages","code":"https://github.com/amazon-science/tanl","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"KEPLER","metrics":{"F1":"71.7"},"uses_additional_data":true,"paper_date":"2019-11-13","paper":"/paper/kepler-a-unified-model-for-knowledge","paper_url":"https://arxiv.org/abs/1911.06136v3","paper_title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","code":"https://github.com/THU-KEG/KEPLER","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":17,"model":"BERTEM+MTB","metrics":{"F1":"71.5","F1 (1% Few-Shot)":"43.4","F1 (10% Few-Shot)":"64.8"},"uses_additional_data":true,"paper_date":"2019-06-07","paper":"/paper/matching-the-blanks-distributional-similarity","paper_url":"https://arxiv.org/abs/1906.03158v1","paper_title":"Matching the Blanks: Distributional Similarity for Relation Learning","code":"https://github.com/plkmo/BERT-Relation-Extraction","n_code_links":13,"syntology":{"n_ran":2,"n_unverified":12,"n_samples":14,"n_pointer_only_licence":1}},{"rank_in_archive_order":18,"model":"KnowBert-W+W","metrics":{"F1":"71.5"},"uses_additional_data":true,"paper_date":"2019-09-09","paper":"/paper/knowledge-enhanced-contextual-word","paper_url":"https://arxiv.org/abs/1909.04164v2","paper_title":"Knowledge Enhanced Contextual Word Representations","code":"https://github.com/allenai/kb","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"DG-SpanBERT-large","metrics":{"F1":"71.5"},"uses_additional_data":false,"paper_date":"2020-04-07","paper":"/paper/efficient-long-distance-relation-extraction","paper_url":"https://arxiv.org/abs/2004.03636v1","paper_title":"Efficient long-distance relation extraction with DG-SpanBERT","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"RELA","metrics":{"F1":"71.2"},"uses_additional_data":false,"paper_date":"2022-12-29","paper":"/paper/sequence-generation-with-label-augmentation","paper_url":"https://arxiv.org/abs/2212.14266v2","paper_title":"Sequence Generation with Label Augmentation for Relation Extraction","code":"https://github.com/pkuserc/rela","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"NLI_RoBERTa","metrics":{"F1":"71.0"},"uses_additional_data":false,"paper_date":"2021-09-08","paper":"/paper/label-verbalization-and-entailment-for","paper_url":"https://arxiv.org/abs/2109.03659v1","paper_title":"Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction","code":"https://github.com/osainz59/Ask2Transformers","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"SpanBERT-large","metrics":{"F1":"70.8"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/spanbert-improving-pre-training-by","paper_url":"https://arxiv.org/abs/1907.10529v3","paper_title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","code":"https://github.com/facebookresearch/SpanBERT","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":4}},{"rank_in_archive_order":23,"model":"GDPNet","metrics":{"F1":"70.5"},"uses_additional_data":false,"paper_date":"2020-12-12","paper":"/paper/gdpnet-refining-latent-multi-view-graph-for","paper_url":"https://arxiv.org/abs/2012.06780v1","paper_title":"GDPNet: Refining Latent Multi-View Graph for Relation Extraction","code":"https://github.com/XueFuzhao/GDPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"Contrastive Pre-training","metrics":{"F1":"69.5"},"uses_additional_data":false,"paper_date":"2020-10-05","paper":"/paper/learning-from-context-or-names-an-empirical","paper_url":"https://arxiv.org/abs/2010.01923v2","paper_title":"Learning from Context or Names? An Empirical Study on Neural Relation Extraction","code":"https://github.com/thunlp/RE-Context-or-Names","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"R-BERT","metrics":{"F1":"69.4"},"uses_additional_data":false,"paper_date":"2019-05-20","paper":"/paper/enriching-pre-trained-language-model-with","paper_url":"https://arxiv.org/abs/1905.08284v1","paper_title":"Enriching Pre-trained Language Model with Entity Information for Relation Classification","code":"https://github.com/monologg/R-BERT","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"C-GCN + PA-LSTM","metrics":{"F1":"68.2"},"uses_additional_data":false,"paper_date":"2018-09-26","paper":"/paper/graph-convolution-over-pruned-dependency","paper_url":"http://arxiv.org/abs/1809.10185v1","paper_title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","code":"https://github.com/qipeng/gcn-over-pruned-trees","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"C-AGGCN","metrics":{"F1":"68.2"},"uses_additional_data":false,"paper_date":"2019-06-18","paper":"/paper/attention-guided-graph-convolutional-networks","paper_url":"https://arxiv.org/abs/1906.07510v8","paper_title":"Attention Guided Graph Convolutional Networks for Relation Extraction","code":"https://github.com/Cartus/AGGCN_TACRED","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":12,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"ERNIE","metrics":{"F1":"67.97"},"uses_additional_data":false,"paper_date":"2019-05-17","paper":"/paper/ernie-enhanced-language-representation-with","paper_url":"https://arxiv.org/abs/1905.07129v3","paper_title":"ERNIE: Enhanced Language Representation with Informative Entities","code":"https://github.com/thunlp/ERNIE","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":29,"model":"BERT-LSTM-base","metrics":{"F1":"67.8"},"uses_additional_data":false,"paper_date":"2019-04-10","paper":"/paper/simple-bert-models-for-relation-extraction","paper_url":"http://arxiv.org/abs/1904.05255v1","paper_title":"Simple BERT Models for Relation Extraction and Semantic Role Labeling","code":"https://github.com/riccorl/transformer-srl","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"SA-LSTM+D","metrics":{"F1":"67.6"},"uses_additional_data":false,"paper_date":"2019-08-10","paper":"/paper/beyond-word-attention-using-segment-attention","paper_url":"https://www.ijcai.org/proceedings/2019/750","paper_title":"Beyond Word Attention: Using Segment Attention in Neural Relation Extraction","code":"https://github.com/yubowen-ph/segment","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"TRE","metrics":{"F1":"67.4"},"uses_additional_data":false,"paper_date":"2019-06-07","paper":"/paper/improving-relation-extraction-by-pre-trained-1","paper_url":"https://arxiv.org/abs/1906.03088v1","paper_title":"Improving Relation Extraction by Pre-trained Language Representations","code":"https://github.com/DFKI-NLP/TRE","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"Alt et al. (2019)","metrics":{"F1":"67.4"},"uses_additional_data":false,"paper_date":"2019-06-07","paper":"/paper/improving-relation-extraction-by-pre-trained-1","paper_url":"https://arxiv.org/abs/1906.03088v1","paper_title":"Improving Relation Extraction by Pre-trained Language Representations","code":"https://github.com/DFKI-NLP/TRE","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"GCN + PA-LSTM","metrics":{"F1":"67.1"},"uses_additional_data":false,"paper_date":"2018-09-26","paper":"/paper/graph-convolution-over-pruned-dependency","paper_url":"http://arxiv.org/abs/1809.10185v1","paper_title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","code":"https://github.com/qipeng/gcn-over-pruned-trees","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"C-SGC","metrics":{"F1":"67.0"},"uses_additional_data":false,"paper_date":"2019-02-19","paper":"/paper/simplifying-graph-convolutional-networks","paper_url":"https://arxiv.org/abs/1902.07153v2","paper_title":"Simplifying Graph Convolutional Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sgc","n_code_links":7,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"C-GCN","metrics":{"F1":"66.4"},"uses_additional_data":false,"paper_date":"2018-09-26","paper":"/paper/graph-convolution-over-pruned-dependency","paper_url":"http://arxiv.org/abs/1809.10185v1","paper_title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","code":"https://github.com/qipeng/gcn-over-pruned-trees","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"PA-LSTM","metrics":{"F1":"65.1"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/position-aware-attention-and-supervised-data","paper_url":"https://aclanthology.org/D17-1004","paper_title":"Position-aware Attention and Supervised Data Improve Slot Filling","code":"https://github.com/yuhaozhang/tacred-relation","n_code_links":2,"syntology":null},{"rank_in_archive_order":37,"model":"AGGCN","metrics":{"F1":"65.1"},"uses_additional_data":false,"paper_date":"2019-06-18","paper":"/paper/attention-guided-graph-convolutional-networks","paper_url":"https://arxiv.org/abs/1906.07510v8","paper_title":"Attention Guided Graph Convolutional Networks for Relation Extraction","code":"https://github.com/Cartus/AGGCN_TACRED","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":12,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"GCN","metrics":{"F1":"64.0"},"uses_additional_data":false,"paper_date":"2018-09-26","paper":"/paper/graph-convolution-over-pruned-dependency","paper_url":"http://arxiv.org/abs/1809.10185v1","paper_title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","code":"https://github.com/qipeng/gcn-over-pruned-trees","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"LLM-QA4RE (XXLarge)","metrics":{"F1":"52.2"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/aligning-instruction-tasks-unlocks-large","paper_url":"https://arxiv.org/abs/2305.11159v1","paper_title":"Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors","code":"https://github.com/osu-nlp-group/qa4re","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"LUKE","metrics":{"F1 (1% Few-Shot)":"17.0","F1 (5% Few-Shot)":"51.6"},"uses_additional_data":true,"paper_date":"2020-10-02","paper":"/paper/luke-deep-contextualized-entity","paper_url":"https://arxiv.org/abs/2010.01057v1","paper_title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":{"n_ran":3,"n_unverified":7,"n_samples":10,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":14,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":13,"distinct_papers_with_any_sample_ran":11,"samples_over_distinct_papers":{"n_ran":34,"n_unverified":75,"n_samples":109,"n_pointer_only_licence":11,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":35,"n_unverified":87,"n_samples":122,"n_pointer_only_licence":11,"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"}}}