{"url":"/dataset/elitr-eca","name":"ELITR ECA","full_name":null,"description_markdown":"The ELITR ECA corpus is a multilingual corpus derived from publications of the European Court of Auditors. We use automatic translation together with Bleualign to identify parallel sentence pairs in all 506 translation directions. The result is a corpus comprising 264k document pairs and 41.9M sentence pairs.\r\n\r\nDescription from: [The ELITR ECA Corpus](https://arxiv.org/pdf/2109.07351v1.pdf)","description_withheld":null,"homepage":"http://data.statmt.org/elitr-eca/","introduced_date":"2021-09-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-elitr-eca-corpus","title":"The ELITR ECA Corpus","first_author":"Philip Williams","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["ELITR ECA"],"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."}