{"url":"/dataset/pattr","name":"PatTR","full_name":"Patent Translation Resource","description_markdown":"**PatTR** is a sentence-parallel corpus extracted from the MAREC patent collection. The current version contains more than 22 million German-English and 18 million French-English parallel sentences collected from all patent text sections as well as 5 million German-French sentence pairs from patent titles, abstracts and claims.\r\n\r\nSource: [PatTR](https://www.cl.uni-heidelberg.de/statnlpgroup/pattr/)","description_withheld":null,"homepage":"https://www.cl.uni-heidelberg.de/statnlpgroup/pattr/","introduced_date":"2012-04-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/structural-and-topical-dimensions-in-multi","title":"Structural and Topical Dimensions in Multi-Task Patent Translation","first_author":"Katharina Waeschle","url":null},"license":{"name":"CC BY-NC-SA 3.0","url":"https://creativecommons.org/licenses/by-nc-sa/3.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Russian","url":"/datasets/language/russian"},{"name":"Persian","url":"/datasets/language/persian"}],"variants":["PatTR"],"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":"2026-09-25T09:33:49+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."}