{"url":"/dataset/genia","name":"GENIA","full_name":null,"description_markdown":"The **GENIA** corpus is the primary collection of biomedical literature compiled and annotated within the scope of the GENIA project. The corpus was created to support the development and evaluation of information extraction and text mining systems for the domain of molecular biology.\r\n\r\nThe corpus contains 1,999 Medline abstracts, selected using a PubMed query for the three MeSH terms “human”, “blood cells”, and “transcription factors”. The corpus has been annotated with various levels of linguistic and semantic information.\r\n\r\nThe primary categories of annotation in the GENIA corpus and the corresponding subcorpora are:\r\n\r\n* Part-of-Speech annotation\r\n* Constituency (phrase structure) syntactic annotation\r\n* Term annotation\r\n* Event annotation\r\n* Relation annotation\r\n* Coreference annotation\r\n\r\nSource: [http://www.geniaproject.org/genia-corpus](http://www.geniaproject.org/genia-corpus)\r\nImage Source: [http://www.geniaproject.org/genia-corpus](http://www.geniaproject.org/genia-corpus)","description_withheld":null,"homepage":"http://bionlp.dbcls.jp/projects/bionlp-st-ge-2016/wiki","introduced_date":"2003-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"GENIA corpus - a semantically annotated corpus for bio-textmining","first_author":null,"url":"http://bioinformatics.oupjournals.org/cgi/content/abstract/19/suppl_1/i180?etoc"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"UIE","url":"/task/uie","datasets_with_task":"/datasets/task/uie"},{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Event Extraction","url":"/task/event-extraction","datasets_with_task":"/datasets/task/event-extraction"},{"name":"Nested Named Entity Recognition","url":"/task/nested-named-entity-recognition","datasets_with_task":"/datasets/task/nested-named-entity-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GENIA","GENIA - LAS","GENIA - UAS","GENIA 2013"],"data_loaders":[],"num_papers_in_archive":121,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/nested-named-entity-recognition-on-genia","task":"Nested Named Entity Recognition","dataset_variant":"GENIA","rows":26,"metrics":["F1"],"first_row_in_archive_order":{"model":"PIQN","paper":"/paper/parallel-instance-query-network-for-named","metrics":{"F1":"81.77"},"code_links":[{"title":"tricktreat/piqn","url":"https://github.com/tricktreat/piqn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/named-entity-recognition-on-genia","task":"Named Entity Recognition (NER)","dataset_variant":"GENIA","rows":14,"metrics":["F1"],"first_row_in_archive_order":{"model":"DeepStruct multi-task w/ finetune","paper":"/paper/deepstruct-pretraining-of-language-models-for-1","metrics":{"F1":"80.8"},"code_links":[{"title":"cgraywang/deepstruct","url":"https://github.com/cgraywang/deepstruct"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/dependency-parsing-on-genia-las","task":"Dependency Parsing","dataset_variant":"GENIA - LAS","rows":3,"metrics":["F1"],"first_row_in_archive_order":{"model":"BiLSTM-CRF","paper":"/paper/from-pos-tagging-to-dependency-parsing-for","metrics":{"F1":"91.92"},"code_links":[{"title":"datquocnguyen/BioNLP","url":"https://github.com/datquocnguyen/BioNLP"},{"title":"datquocnguyen/BioPosDep","url":"https://github.com/datquocnguyen/BioPosDep"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/dependency-parsing-on-genia-uas","task":"Dependency Parsing","dataset_variant":"GENIA - UAS","rows":3,"metrics":["F1"],"first_row_in_archive_order":{"model":"BiLSTM-CRF","paper":"/paper/from-pos-tagging-to-dependency-parsing-for","metrics":{"F1":"92.84"},"code_links":[{"title":"datquocnguyen/BioNLP","url":"https://github.com/datquocnguyen/BioNLP"},{"title":"datquocnguyen/BioPosDep","url":"https://github.com/datquocnguyen/BioPosDep"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/event-extraction-on-genia","task":"Event Extraction","dataset_variant":"GENIA","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"DeepEventMine","paper":"/paper/deepeventmine-end-to-end-neural-nested-event","metrics":{"F1":"63.96"},"code_links":[{"title":"aistairc/DeepEventMine","url":"https://github.com/aistairc/DeepEventMine"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/event-extraction-on-genia-2013","task":"Event Extraction","dataset_variant":"GENIA 2013","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"DeepEventMine","paper":"/paper/deepeventmine-end-to-end-neural-nested-event","metrics":{"F1":"56.72"},"code_links":[{"title":"aistairc/DeepEventMine","url":"https://github.com/aistairc/DeepEventMine"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/uie-on-genia","task":"UIE","dataset_variant":"GENIA","rows":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"KnowCoder-7b-IE","paper":"/paper/knowcoder-coding-structured-knowledge-into","metrics":{"F1 score":"76.7"},"code_links":[{"title":"ICT-GoKnow/KnowCoder","url":"https://github.com/ICT-GoKnow/KnowCoder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/to-be-continuous-or-to-be-discrete-those-are","title":"To be Continuous, or to be Discrete, Those are Bits of Questions","date":"2024-06-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":5,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/comparing-and-combining-some-popular-ner","title":"Comparing and combining some popular NER approaches on Biomedical tasks","date":"2023-05-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/diffusionner-boundary-diffusion-for-named","title":"DiffusionNER: Boundary Diffusion for Named Entity Recognition","date":"2023-05-22","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/optimizing-bi-encoder-for-named-entity","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","date":"2022-08-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-embarrassingly-easy-but-strong-baseline","title":"An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognition","date":"2022-08-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deepstruct-pretraining-of-language-models-for-1","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","date":"2022-05-21","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":7,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/biobart-pretraining-and-evaluation-of-a","title":"BioBART: Pretraining and Evaluation of A Biomedical Generative Language Model","date":"2022-04-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/parallel-instance-query-network-for-named","title":"Parallel Instance Query Network for Named Entity Recognition","date":"2022-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-named-entity-recognition-as-word-word","title":"Unified Named Entity Recognition as Word-Word Relation Classification","date":"2021-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fusing-heterogeneous-factors-with-triaffine","title":"Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition","date":"2021-10-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nested-named-entity-recognition-via","title":"Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path","date":"2021-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-unified-generative-framework-for-various","title":"A Unified Generative Framework for Various NER Subtasks","date":"2021-06-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-sequence-to-set-network-for-nested-named","title":"A Sequence-to-Set Network for Nested Named Entity Recognition","date":"2021-05-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":5,"samples_unverified":0,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/locate-and-label-a-two-stage-identifier-for","title":"Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition","date":"2021-05-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nested-named-entity-recognition-with","title":"Nested Named Entity Recognition with Partially-Observed TreeCRFs","date":"2020-12-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/biomedical-event-extraction-on-graph-edge","title":"Biomedical Event Extraction with Hierarchical Knowledge Graphs","date":"2020-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pyramid-a-layered-model-for-nested-named","title":"Pyramid: A Layered Model for Nested Named Entity Recognition","date":"2020-07-01","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/deepeventmine-end-to-end-neural-nested-event","title":"DeepEventMine: end-to-end neural nested event extraction from biomedical texts","date":"2020-06-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/named-entity-recognition-as-dependency","title":"Named Entity Recognition as Dependency Parsing","date":"2020-05-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bipartite-flat-graph-network-for-nested-named","title":"Bipartite Flat-Graph Network for Nested Named Entity Recognition","date":"2020-05-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-boundary-aware-neural-model-for-nested","title":"A Boundary-aware Neural Model for Nested Named Entity Recognition","date":"2019-11-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/nested-named-entity-recognition-via-second","title":"Nested Named Entity Recognition via Second-best Sequence Learning and Decoding","date":"2019-09-05","rows_on_this_dataset":5,"code_links":3,"syntology":null},{"paper":"/paper/neural-architectures-for-nested-ner-through-1","title":"Neural Architectures for Nested NER through Linearization","date":"2019-08-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/sequence-to-nuggets-nested-entity-mention","title":"Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks","date":"2019-06-10","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/scibert-pretrained-contextualized-embeddings","title":"SciBERT: A Pretrained Language Model for Scientific Text","date":"2019-03-26","rows_on_this_dataset":4,"code_links":6,"syntology":null},{"paper":"/paper/neural-segmental-hypergraphs-for-overlapping","title":"Neural Segmental Hypergraphs for Overlapping Mention Recognition","date":"2018-10-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-neural-transition-based-model-for-nested","title":"A Neural Transition-based Model for Nested Mention Recognition","date":"2018-10-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/from-pos-tagging-to-dependency-parsing-for","title":"From POS tagging to dependency parsing for biomedical event extraction","date":"2018-08-11","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/a-neural-layered-model-for-nested-named","title":"A Neural Layered Model for Nested Named Entity Recognition","date":"2018-06-01","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":44,"samples_ran":24,"samples_unverified":20,"pointer_only_for_licence":5,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}