{"url":"/dataset/fin","name":"FIN","full_name":null,"description_markdown":"A dataset of financial agreements made public through U.S. Security and Exchange Commission (SEC) filings. Eight documents (totalling 54,256 words) were randomly selected for manual annotation, based on the four NE types provided in the CoNLL-2003 dataset: LOCATION (LOC), ORGANISATION (ORG), PERSON (PER), and MISCELLANEOUS (MISC).","description_withheld":null,"homepage":"","introduced_date":"2015-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/domain-adaption-of-named-entity-recognition","title":"Domain Adaption of Named Entity Recognition to Support Credit Risk Assessment","first_author":"Julio Cesar Salinas Alvarado","url":null},"license":null,"modalities":[],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"}],"languages":[],"variants":["FIN"],"data_loaders":[],"num_papers_in_archive":39,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}