{"url":"/dataset/kurdishinterdialect","name":"KurdishInterdialect","full_name":"Kurdish parallel corpus in Kurmanji, Sorani and English","description_markdown":"a parallel corpus of Sorani (ckb or Central Kurdish) and Kurmanji (kmr or Northern Kurdish) dialects of Kurdish along with English (eng). The parallel corpus contains three manually-aligned corpus in Sorani-Kurmanji, Sorani-English and Kurmanji-English in various formats, namely Translation Memory eXchange file format (.tmx), parallel annotated text useful for ParaConc and raw parallel texts (.txt). \r\nThis corpus contains 12,327 translation pairs in the two major dialects of Kurdish, Sorani and Kurmanji. We also provide 1,797 and 650 translation pairs in English-Kurmanji and English-Sorani.","description_withheld":null,"homepage":"https://github.com/KurdishBLARK/InterdialectCorpus","introduced_date":"2020-10-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/leveraging-multilingual-news-websites-for","title":"Leveraging Multilingual News Websites for Building a Kurdish Parallel Corpus","first_author":"Sina Ahmadi","url":null},"license":null,"modalities":[],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Low-Resource Neural Machine Translation","url":"/task/low-resource-neural-machine-translation","datasets_with_task":"/datasets/task/low-resource-neural-machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Northern Kurdish","url":"/datasets/language/northern-kurdish"},{"name":"Central Kurdish","url":"/datasets/language/central-kurdish"},{"name":"Kurdish","url":"/datasets/language/kurdish"}],"variants":["KurdishInterdialect"],"data_loaders":[],"num_papers_in_archive":1,"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."}