{"url":"/sota/coreference-resolution-on-ontonotes","task":{"name":"Coreference Resolution","url":"/task/coreference-resolution","note":null},"dataset":{"name":"OntoNotes","url":"/dataset/ontonotes-5-0"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Coreference resolution is the task of clustering mentions in text that refer to the same underlying real world entities.\n\nExample:\n\n```\n               +-----------+\n               |           |\nI voted for Obama because he was most aligned with my values\", she said.\n |                                                 |            |\n +-------------------------------------------------+------------+\n```\n\n\"I\", \"my\", and \"she\" belong to the same cluster and \"Obama\" and \"he\" belong to the same cluster.","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"],"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"}},"counts":{"rows":26,"rows_with_code":24,"rows_with_paper_page":26,"rows_dated":26,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Maverick_mes","metrics":{"F1":"83.6"},"uses_additional_data":false,"paper_date":"2024-07-31","paper":"/paper/2407-21489","paper_url":"https://arxiv.org/abs/2407.21489v1","paper_title":"Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends","code":"https://github.com/sapienzanlp/maverick-coref","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":2,"model":"seq2seq","metrics":{"F1":"83.3"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/coreference-resolution-through-a-seq2seq","paper_url":"https://arxiv.org/abs/2211.12142v1","paper_title":"Coreference Resolution through a seq2seq Transition-Based System","code":"https://github.com/google-research/google-research","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"ASP+T0-3B","metrics":{"F1":"82.3"},"uses_additional_data":false,"paper_date":"2022-10-26","paper":"/paper/autoregressive-structured-prediction-with","paper_url":"https://arxiv.org/abs/2210.14698v2","paper_title":"Autoregressive Structured Prediction with Language Models","code":"https://github.com/lyutyuh/asp","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"caw-coref + RoBERTa","metrics":{"F1":"81.6"},"uses_additional_data":false,"paper_date":"2023-10-09","paper":"/paper/caw-coref-conjunction-aware-word-level","paper_url":"https://arxiv.org/abs/2310.06165v2","paper_title":"CAW-coref: Conjunction-Aware Word-level Coreference Resolution","code":"https://github.com/kareldo/wl-coref","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"LingMess","metrics":{"F1":"81.4"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/lingmess-linguistically-informed-multi-expert","paper_url":"https://arxiv.org/abs/2205.12644v3","paper_title":"LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution","code":"https://github.com/shon-otmazgin/fastcoref","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"wl-coref + RoBERTa","metrics":{"F1":"81"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/word-level-coreference-resolution","paper_url":"https://arxiv.org/abs/2109.04127v1","paper_title":"Word-Level Coreference Resolution","code":"https://github.com/vdobrovolskii/wl-coref","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"U-MEM + Longformer","metrics":{"F1":"80.9"},"uses_additional_data":false,"paper_date":"2022-08-30","paper":"/paper/efficient-and-interpretable-neural-models-for","paper_url":"https://arxiv.org/abs/2208.14252v1","paper_title":"Efficient and Interpretable Neural Models for Entity Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"longdoc S (OntoNotes + 60k pseudo-singletons)","metrics":{"F1":"80.6"},"uses_additional_data":false,"paper_date":"2021-09-20","paper":"/paper/on-generalization-in-coreference-resolution","paper_url":"https://arxiv.org/abs/2109.09667v1","paper_title":"On Generalization in Coreference Resolution","code":"https://github.com/shtoshni/fast-coref","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"G2GT SpanBERT-large reduced","metrics":{"F1":"80.5"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/graph-refinement-for-coreference-resolution-1","paper_url":"https://arxiv.org/abs/2203.16574v1","paper_title":"Graph Refinement for Coreference Resolution","code":"https://github.com/idiap/g2g-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"G2GT SpanBERT-large overlap","metrics":{"F1":"80.2"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/graph-refinement-for-coreference-resolution-1","paper_url":"https://arxiv.org/abs/2203.16574v1","paper_title":"Graph Refinement for Coreference Resolution","code":"https://github.com/idiap/g2g-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"SpanBERT","metrics":{"F1":"79.6"},"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":12,"model":"U-MEM* + SpanBERT","metrics":{"F1":"79.6"},"uses_additional_data":false,"paper_date":"2020-10-06","paper":"/paper/learning-to-ignore-long-document-coreference","paper_url":"https://arxiv.org/abs/2010.02807v3","paper_title":"Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks","code":"https://github.com/shtoshni/fast-coref","n_code_links":3,"syntology":null},{"rank_in_archive_order":13,"model":"longdoc S (ON + PreCo + LitBank + 30k pseudo-singletons)","metrics":{"F1":"79.6"},"uses_additional_data":false,"paper_date":"2021-09-20","paper":"/paper/on-generalization-in-coreference-resolution","paper_url":"https://arxiv.org/abs/2109.09667v1","paper_title":"On Generalization in Coreference Resolution","code":"https://github.com/shtoshni/fast-coref","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"longdoc S (OntoNotes + PreCo + LitBank)","metrics":{"F1":"79.2"},"uses_additional_data":false,"paper_date":"2021-09-20","paper":"/paper/on-generalization-in-coreference-resolution","paper_url":"https://arxiv.org/abs/2109.09667v1","paper_title":"On Generalization in Coreference Resolution","code":"https://github.com/shtoshni/fast-coref","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"BERT-large","metrics":{"F1":"76.9"},"uses_additional_data":false,"paper_date":"2019-08-24","paper":"/paper/bert-for-coreference-resolution-baselines-and","paper_url":"https://arxiv.org/abs/1908.09091v4","paper_title":"BERT for Coreference Resolution: Baselines and Analysis","code":"https://github.com/mandarjoshi90/coref","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"BERT + EE","metrics":{"F1":"76.61"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/coreference-resolution-with-entity","paper_url":"https://aclanthology.org/P19-1066","paper_title":"Coreference Resolution with Entity Equalization","code":"https://github.com/kkjawz/coref-ee","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"BERT-base","metrics":{"F1":"73.9"},"uses_additional_data":false,"paper_date":"2019-08-24","paper":"/paper/bert-for-coreference-resolution-baselines-and","paper_url":"https://arxiv.org/abs/1908.09091v4","paper_title":"BERT for Coreference Resolution: Baselines and Analysis","code":"https://github.com/mandarjoshi90/coref","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"Reinforced + ELMo","metrics":{"F1":"73.8"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/end-to-end-deep-reinforcement-learning-based","paper_url":"https://aclanthology.org/P19-1064","paper_title":"End-to-end Deep Reinforcement Learning Based Coreference Resolution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"c2f-coref","metrics":{"F1":"73.0"},"uses_additional_data":false,"paper_date":"2018-04-15","paper":"/paper/higher-order-coreference-resolution-with","paper_url":"http://arxiv.org/abs/1804.05392v1","paper_title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","code":"https://github.com/kentonl/e2e-coref","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":21,"n_samples":23,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"e2e-coref + ELMo + hyperparameter tuning","metrics":{"F1":"72.3"},"uses_additional_data":false,"paper_date":"2018-04-15","paper":"/paper/higher-order-coreference-resolution-with","paper_url":"http://arxiv.org/abs/1804.05392v1","paper_title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","code":"https://github.com/kentonl/e2e-coref","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":21,"n_samples":23,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"e2e-coref + ELMo","metrics":{"F1":"70.4"},"uses_additional_data":false,"paper_date":"2018-02-15","paper":"/paper/deep-contextualized-word-representations","paper_url":"http://arxiv.org/abs/1802.05365v2","paper_title":"Deep contextualized word representations","code":"https://github.com/flairNLP/flair","n_code_links":46,"syntology":{"n_ran":23,"n_unverified":35,"n_samples":58,"n_pointer_only_licence":25}},{"rank_in_archive_order":22,"model":"E2E-CR + ASL","metrics":{"F1":"67.8"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/learning-word-representations-with-cross","paper_url":"https://aclanthology.org/D18-1518","paper_title":"Learning Word Representations with Cross-Sentence Dependency for End-to-End Co-reference Resolution","code":"https://github.com/luohongyin/coatt-coref","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"e2e-coref","metrics":{"F1":"67.2"},"uses_additional_data":false,"paper_date":"2017-07-21","paper":"/paper/end-to-end-neural-coreference-resolution","paper_url":"http://arxiv.org/abs/1707.07045v2","paper_title":"End-to-end Neural Coreference Resolution","code":"https://github.com/kentonl/e2e-coref","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":24,"model":"Reward Rescaling","metrics":{"F1":"65.73"},"uses_additional_data":false,"paper_date":"2016-09-27","paper":"/paper/deep-reinforcement-learning-for-mention","paper_url":"http://arxiv.org/abs/1609.08667v3","paper_title":"Deep Reinforcement Learning for Mention-Ranking Coreference Models","code":"https://github.com/clarkkev/deep-coref","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":25,"model":"NN Cluster Ranker","metrics":{"F1":"65.29"},"uses_additional_data":false,"paper_date":"2016-06-04","paper":"/paper/improving-coreference-resolution-by-learning","paper_url":"http://arxiv.org/abs/1606.01323v2","paper_title":"Improving Coreference Resolution by Learning Entity-Level Distributed Representations","code":"https://github.com/clarkkev/deep-coref","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":26,"model":"Global","metrics":{"F1":"64.21"},"uses_additional_data":false,"paper_date":"2016-04-11","paper":"/paper/learning-global-features-for-coreference","paper_url":"http://arxiv.org/abs/1604.03035v1","paper_title":"Learning Global Features for Coreference Resolution","code":"https://github.com/swiseman/nn_coref","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":9,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":37,"n_unverified":86,"n_samples":123,"n_pointer_only_licence":45,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":39,"n_unverified":107,"n_samples":146,"n_pointer_only_licence":45,"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"}}}