{"url":"/dataset/litbank","name":"LitBank","full_name":"LitBank","description_markdown":"LitBank is an annotated dataset of 100 works of English-language fiction to support tasks in natural language processing and the computational humanities, described in more detail in the following publications:\r\n\r\n- David Bamman, Sejal Popat and Sheng Shen (2019), \"An Annotated Dataset of Literary Entities,\" NAACL 2019.\r\n- Matthew Sims, Jong Ho Park and David Bamman (2019), \"Literary Event Detection,\" ACL 2019.\r\n- David Bamman, Olivia Lewke and Anya Mansoor (2020), \"An Annotated Dataset of Coreference in English Literature\", LREC.\r\n\r\nLitBank currently contains annotations for entities, events, entity coreference, and quotation attribution in a sample of ~2,000 words from each of those texts, totaling 210,532 tokens.\r\n\r\nLitBank is licensed under a Creative Commons Attribution 4.0 International License.","description_withheld":null,"homepage":"https://github.com/dbamman/litbank","introduced_date":"2019-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/an-annotated-dataset-of-literary-entities","title":"An annotated dataset of literary entities","first_author":"David Bamman","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"}],"languages":[],"variants":["LitBank"],"data_loaders":[{"repo":"https://github.com/dbamman/litbank","url":"https://github.com/dbamman/litbank","frameworks":["pytorch"]}],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/coreference-resolution-on-litbank","task":"Coreference Resolution","dataset_variant":"LitBank","rows":2,"metrics":["Avg F1","F1"],"first_row_in_archive_order":{"model":"Maverick_incr","paper":"/paper/2407-21489","metrics":{"Avg F1":"78.3"},"code_links":[{"title":"sapienzanlp/maverick-coref","url":"https://github.com/sapienzanlp/maverick-coref"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/2407-21489","title":"Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends","date":"2024-07-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/on-generalization-in-coreference-resolution","title":"On Generalization in Coreference Resolution","date":"2021-09-20","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":11,"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."}