{"url":"/sota/drug-drug-interaction-extraction-on-ddi","task":{"name":"Drug–drug Interaction Extraction","url":"/task/drug-drug-interaction-extraction","note":null},"dataset":{"name":"DDI extraction 2013 corpus","url":"/dataset/ddi"},"category":"Natural Language Processing","categories":["Medical","Natural Language Processing"],"category_note":null,"description":"Automatic extraction of Drug-drug interaction (DDI) information from the biomedical literature.\r\n\r\n( Image credit: [Using Drug Descriptions and Molecular Structures for Drug-Drug Interaction Extraction from Literature](https://watermark.silverchair.com/btaa907.pdf?token=AQECAHi208BE49Ooan9kkhW_Ercy7Dm3ZL_9Cf3qfKAc485ysgAAAuAwggLcBgkqhkiG9w0BBwagggLNMIICyQIBADCCAsIGCSqGSIb3DQEHATAeBglghkgBZQMEAS4wEQQMb9BaAetiYVbvf0_9AgEQgIICk0-IUccCHnqrDDtbnyBSTvPnrWXc4F2vfEMKkxzGRA3-WbynJbw0HptyHyjawXr3c4TeC9ZhIta1szzhc5t1JOhdh8rOo5CTtGk_JPfq14TkMkIISDCvdsVL76fvCn-3KhtAJhHPcyYTDqMaGSb3ltXJLfR6PXoCXnINprcZ3pO6ktuNLA8KF0_CHTITnGNcX1G1n6ZERyGTPwGjodH9Qq9UcYzJCx4N1KKgxOMAj5oxIoLPQi97oNJ3eCoYBoKDuSW-Zza_ULcBDXkkTvt3A460O32vfRAqnnPYlVSuvEiASc3lX8O6Qb28GXc99EIzwDQJEO4znl7haAGOxubuUm5Of9p22xRfc7KSuCh41cJxW_31bsnTuf8Sb2z6O6bFo3aNlxF3SrLfNTHfJH6Tst0WvaaRJ1gQ3JxcFwu--hsZMF9bW3_yzFwP1ZnVIPVtE0bqm3QZt-_nHaE4o9KgCCNY4t70h7U7yD9ZrZMvFnNieSvgL35t--l5PerE9uZgP6v9LUKUyAI1TDHHMameO5794Z7WII8v_MKG0jmUIbr564ENnyKJYunNowu3EbvUMxBv3DSUkepU1kP66tJjSflal3LlRd8LUbj4m2Tin3LteS-09Gje4pyMaeO5RywX_tSPSFGK8QGaZqpgbIU2y23YnCMAnIDOSS3_L3LQRGu50YK5OwEvMY7azpEMbR3kaaHWu_cmEN2Vm61UdG6uLql5pMc9zKfGAQ3E1VXGuhdEalRtuLbtBZ9UFj-vYePfrRGWRXjkg-11SGgKqRaJcLK32yuvhG11KqacCoY169A4G29_GfRC3rbDsnqyMRZ9ESe3FB1NnWwZ4HPNA7ju3yJ7cfZSfYgdygT6oTpBQjaweH5U) )","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","Micro 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","Micro F1":"higher"}},"counts":{"rows":10,"rows_with_code":6,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"DESC+MOL+SciBERT","metrics":{"F1":"0.8408","Micro F1":"84.08"},"uses_additional_data":false,"paper_date":"2020-10-24","paper":"/paper/using-drug-descriptions-and-molecular","paper_url":"https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btaa907/5938075#209442351","paper_title":"Using Drug Descriptions and Molecular Structures for Drug-Drug Interaction Extraction from Literature","code":"https://github.com/tticoin/DESC_MOL-DDIE","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SciFive-large","metrics":{"F1":"0.8367","Micro F1":"83.67"},"uses_additional_data":false,"paper_date":"2021-05-28","paper":"/paper/scifive-a-text-to-text-transformer-model-for","paper_url":"https://arxiv.org/abs/2106.03598v1","paper_title":"SciFive: a text-to-text transformer model for biomedical literature","code":"https://github.com/justinphan3110/SciFive","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PubMedBERT","metrics":{"F1":"0.8236","Micro F1":"82.36"},"uses_additional_data":false,"paper_date":"2020-07-31","paper":"/paper/domain-specific-language-model-pretraining","paper_url":"https://arxiv.org/abs/2007.15779v6","paper_title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","code":"https://github.com/bionlu-coling2024/biomed-ner-intent_detection","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"BioBERT","metrics":{"F1":"0.8088","Micro F1":"80.88"},"uses_additional_data":false,"paper_date":"2019-01-25","paper":"/paper/biobert-a-pre-trained-biomedical-language","paper_url":"https://arxiv.org/abs/1901.08746v4","paper_title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","code":"https://github.com/dmis-lab/biobert","n_code_links":19,"syntology":{"n_ran":4,"n_unverified":21,"n_samples":25,"n_pointer_only_licence":1}},{"rank_in_archive_order":5,"model":"Hierarchy Bi-LSTMs +Att.+SDP","metrics":{"F1":"0.729","Micro F1":"72.9"},"uses_additional_data":false,"paper_date":"2017-10-25","paper":"/paper/drug-drug-interaction-extraction-via-1","paper_url":"https://academic.oup.com/bioinformatics/article/34/5/828/4565590","paper_title":"Drug–drug interaction extraction via hierarchical RNNs on sequence and shortest dependency paths","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"MOL+CNN","metrics":{"F1":"0.7255","Micro F1":"72.55"},"uses_additional_data":false,"paper_date":"2018-05-15","paper":"/paper/enhancing-drug-drug-interaction-extraction","paper_url":"http://arxiv.org/abs/1805.05593v1","paper_title":"Enhancing Drug-Drug Interaction Extraction from Texts by Molecular Structure Information","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Graph Kernel-based method","metrics":{"F1":"0.684","Micro F1":"68.4"},"uses_additional_data":false,"paper_date":"2016-03-21","paper":"/paper/a-graph-kernel-based-on-context-vectors-for","paper_url":"https://www.sciencedirect.com/science/article/pii/S1532046416300053","paper_title":"A graph kernel based on context vectors for extracting drug–drug interactions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Feature-based SVM","metrics":{"F1":"0.670","Micro F1":"67.0"},"uses_additional_data":false,"paper_date":"2015-03-19","paper":"/paper/extracting-drug-drug-interactions-from","paper_url":"https://www.sciencedirect.com/science/article/pii/S1532046415000441","paper_title":"Extracting drug–drug interactions from literature using a rich feature-based linear kernel approach","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"CharacterBERT (base, medical)","metrics":{"Micro F1":"80.38"},"uses_additional_data":false,"paper_date":"2020-10-20","paper":"/paper/characterbert-reconciling-elmo-and-bert-for","paper_url":"https://arxiv.org/abs/2010.10392v3","paper_title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","code":"https://github.com/helboukkouri/character-bert","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"ELECTRAMed","metrics":{"Micro F1":"79.13"},"uses_additional_data":true,"paper_date":"2021-04-19","paper":"/paper/electramed-a-new-pre-trained-language","paper_url":"https://arxiv.org/abs/2104.09585v1","paper_title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","code":"https://github.com/gmpoli/electramed","n_code_links":2,"syntology":null}],"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":3,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":9,"n_unverified":29,"n_samples":38,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":9,"n_unverified":29,"n_samples":38,"n_pointer_only_licence":1,"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"}}}