{"url":"/dataset/wmt-2018","name":"WMT 2018","full_name":null,"description_markdown":"**WMT 2018** is a collection of datasets used in shared tasks of the Third Conference on Machine Translation. The conference builds on a series of twelve previous annual workshops and conferences on Statistical Machine Translation.\r\n\r\nThe conference featured ten shared tasks:\r\n\r\n- a news translation task,\r\n- a biomedical translation task,\r\n- a multimodal machine translation task,\r\n- a metrics task,\r\n- a quality estimation task,\r\n- an automatic post-editing task,\r\n- a parallel corpus filtering task.\r\n\r\nSource: [http://www.statmt.org/wmt18/](http://www.statmt.org/wmt18/)","description_withheld":null,"homepage":"http://www.statmt.org/wmt18/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/findings-of-the-2018-conference-on-machine","title":"Findings of the 2018 Conference on Machine Translation (WMT18)","first_author":"Ond{\\v{r}}ej Bojar","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Translation deu-eng","url":"/task/translation-deu-eng","datasets_with_task":"/datasets/task/translation-deu-eng"},{"name":"Translation eng-deu","url":"/task/translation-eng-deu","datasets_with_task":"/datasets/task/translation-eng-deu"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Finnish","url":"/datasets/language/finnish"}],"variants":["newstest2018-ende eng-deu","newstest2018-deen deu-eng","newstest2018-ende","newstest2018-deen","WMT 2018 Estonian-English","WMT 2018 English-Estonian","WMT 2018","WMT 2018 Finnish-English","WMT 2018 English-Finnish"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wmt/wmt18","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lintang/wmt18","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wmt18","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":37,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/machine-translation-on-wmt-2018-finnish","task":"Machine Translation","dataset_variant":"WMT 2018 Finnish-English","rows":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"CT+B/S construction","paper":"/paper/the-university-of-sydneys-machine-translation","metrics":{"BLEU":"26.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt-2018-english","task":"Machine Translation","dataset_variant":"WMT 2018 English-Estonian","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Multi-pass backtranslated adapted transformer","paper":"/paper/tildes-machine-translation-systems-for-wmt","metrics":{"BLEU":"24.10"},"code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt-2018-english-1","task":"Machine Translation","dataset_variant":"WMT 2018 English-Finnish","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Transformer trained on highly filtered data","paper":"/paper/impact-of-corpora-quality-on-neural-machine","metrics":{"BLEU":"17.40"},"code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-wmt-2018-estonian","task":"Machine Translation","dataset_variant":"WMT 2018 Estonian-English","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"Multi-pass backtranslated adapted transformer","paper":"/paper/tildes-machine-translation-systems-for-wmt","metrics":{"BLEU":"29.00"},"code_links":[{"title":"M4t1ss/parallel-corpora-tools","url":"https://github.com/M4t1ss/parallel-corpora-tools"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-university-of-sydneys-machine-translation","title":"The University of Sydney's Machine Translation System for WMT19","date":"2019-06-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/impact-of-corpora-quality-on-neural-machine","title":"Impact of Corpora Quality on Neural Machine Translation","date":"2018-10-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tildes-machine-translation-systems-for-wmt","title":"Tilde's Machine Translation Systems for WMT 2018","date":"2018-10-01","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"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."}