{"url":"/dataset/tydip","name":"TyDiP","full_name":"A Dataset for Politeness Classification in Nine Typologically Diverse Languages","description_markdown":"**A Dataset for Politeness Classification in Nine Typologically Diverse Languages (TyDiP)** is a dataset containing three-way politeness annotations for 500 examples in each language, totaling 4.5K examples.\r\n\r\nSource: [TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages](https://arxiv.org/pdf/2211.16496v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.16496v1.pdf](https://arxiv.org/pdf/2211.16496v1.pdf)","description_withheld":null,"homepage":"https://github.com/genius1237/tydip","introduced_date":"2022-11-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/tydip-a-dataset-for-politeness-classification","title":"TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages","first_author":"Anirudh Srinivasan","url":null},"license":{"name":"CC BY 4.0 License","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Afrikaans","url":"/datasets/language/afrikaans"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["TyDiP"],"data_loaders":[],"num_papers_in_archive":3,"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."}