{"url":"/dataset/ipm-nel","name":"IPM NEL","full_name":"Derczynski IPM Named Entity Linking","description_markdown":"This data is for the task of named entity recognition and linking/disambiguation over tweets. It comprises\r\nthe addition of an entity URI layer on top of an NER-annotated tweet dataset. The task is to detect entities\r\nand then provide a correct link to them in DBpedia, thus disambiguating otherwise ambiguous entity surface\r\nforms; for example, this means linking \"Paris\" to the correct instance of a city named that (e.g. Paris, \r\nFrance vs. Paris, Texas).\r\n\r\nThe data concentrates on ten types of named entities: company, facility, geographic location, movie, musical\r\nartist, person, product, sports team, TV show, and other.\r\n\r\nThe file is tab separated, in CoNLL format, with line breaks between tweets.\r\nData preserves the tokenisation used in the Ritter datasets.\r\nPoS labels are not present for all tweets, but where they could be found in the Ritter\r\ndata, they're given. In cases where a URI could not be agreed, or was not present in\r\nDBpedia, there is a NIL. See the paper for a full description of the methodology.","description_withheld":null,"homepage":"","introduced_date":"2014-10-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/analysis-of-named-entity-recognition-and","title":"Analysis of Named Entity Recognition and Linking for Tweets","first_author":"Leon Derczynski","url":null},"license":{"name":"CC-BY 4.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Derczynski","IPM NEL"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/strombergnlp/ipm_nel","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":32,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/entity-linking-on-derczynski-1","task":"Entity Linking","dataset_variant":"Derczynski","rows":7,"metrics":["Micro-F1","Micro-F1 strong"],"first_row_in_archive_order":{"model":"ReLiK-Large","paper":"/paper/2408-00103","metrics":{"Micro-F1":"56.3"},"code_links":[{"title":"SapienzaNLP/relik","url":"https://github.com/SapienzaNLP/relik"},{"title":"RadeenXALNW/G-RAG_1.0","url":"https://github.com/RadeenXALNW/G-RAG_1.0"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/2408-00103","title":"ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget","date":"2024-07-31","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/entity-disambiguation-via-fusion-entity","title":"Entity Disambiguation via Fusion Entity Decoding","date":"2024-04-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/refined-an-efficient-zero-shot-capable-1","title":"ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking","date":"2022-07-08","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/autoregressive-entity-retrieval","title":"Autoregressive Entity Retrieval","date":"2020-10-02","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/rel-an-entity-linker-standing-on-the","title":"REL: An Entity Linker Standing on the Shoulders of Giants","date":"2020-06-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/end-to-end-neural-entity-linking","title":"End-to-End Neural Entity Linking","date":"2018-08-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"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":2,"samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":2,"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."}