{"url":"/dataset/figer","name":"FIGER","full_name":"Fine-Grained Entity Recognition","description_markdown":"The **FIGER** dataset is an entity recognition dataset where entities are labelled using fine-grained system 112 tags, such as *person/doctor*, *art/written_work* and *building/hotel*. The tags are derivied from Freebase types. The training set consists of Wikipedia articles automatically annotated with distant supervision approach that utilizes the information encoded in anchor links. The test set was annotated manually.\r\n\r\nSource: [http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/5152](http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/5152)","description_withheld":null,"homepage":"http://xiaoling.github.io/figer/","introduced_date":"2012-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Fine-Grained Entity Recognition","first_author":null,"url":"http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/5152"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Entity Typing","url":"/task/entity-typing","datasets_with_task":"/datasets/task/entity-typing"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FIGER"],"data_loaders":[],"num_papers_in_archive":96,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/entity-linking-on-figer","task":"Entity Linking","dataset_variant":"FIGER","rows":1,"metrics":["Accuracy","Macro F1","Micro F1"],"first_row_in_archive_order":{"model":"ERNIE","paper":"/paper/ernie-enhanced-language-representation-with","metrics":{"Accuracy":"57.19","Macro F1":"76.51","Micro F1":"73.39"},"code_links":[{"title":"thunlp/ERNIE","url":"https://github.com/thunlp/ERNIE"},{"title":"Mind23-2/MindCode-136","url":"https://github.com/Mind23-2/MindCode-136"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/entity-typing-on-figer","task":"Entity Typing","dataset_variant":"FIGER","rows":1,"metrics":["Macro F1","Micro F1"],"first_row_in_archive_order":{"model":"LITE","paper":"/paper/ultra-fine-entity-typing-with-indirect","metrics":{"Macro F1":"80.1","Micro F1":"83.3"},"code_links":[{"title":"luka-group/lite","url":"https://github.com/luka-group/lite"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ultra-fine-entity-typing-with-indirect","title":"Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference","date":"2022-02-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ernie-enhanced-language-representation-with","title":"ERNIE: Enhanced Language Representation with Informative Entities","date":"2019-05-17","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":1,"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."}