{"url":"/dataset/muse","name":"MUSE","full_name":"MUSE","description_markdown":"The **MUSE** dataset contains bilingual dictionaries for 110 pairs of languages. For each language pair, the training seed dictionaries contain approximately 5000 word pairs while the evaluation sets contain 1500 word pairs.\r\n\r\nSource: [Filtered Inner Product Projection for Multilingual Embedding Alignment](https://arxiv.org/abs/2006.03652)\r\nImage Source: [https://github.com/facebookresearch/MUSE](https://github.com/facebookresearch/MUSE)","description_withheld":null,"homepage":"https://github.com/facebookresearch/MUSE","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC BY-NC 4.0","url":"https://github.com/facebookresearch/MUSE/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Word Alignment","url":"/task/word-alignment","datasets_with_task":"/datasets/task/word-alignment"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["MUSE Italian-French","MUSE English-Spanish","MUSE English-French","MUSE English-Portuguese","MUSE en-pt","MUSE en-de","MUSE"],"data_loaders":[{"repo":"https://github.com/facebookresearch/MUSE","url":"https://github.com/facebookresearch/MUSE","frameworks":["pytorch"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/word-alignment-on-muse-en-de","task":"Word Alignment","dataset_variant":"MUSE en-de","rows":1,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper":"/paper/unsupervised-multilingual-alignment-using","metrics":{"P@1":"74.08"},"code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/word-alignment-on-muse-en-pt","task":"Word Alignment","dataset_variant":"MUSE en-pt","rows":1,"metrics":["P@1"],"first_row_in_archive_order":{"model":"Barycenter Alignment","paper":"/paper/unsupervised-multilingual-alignment-using","metrics":{"P@1":"84.65"},"code_links":[{"title":"alixxxin/multi-lang","url":"https://github.com/alixxxin/multi-lang"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/unsupervised-multilingual-alignment-using","title":"Unsupervised Multilingual Alignment using Wasserstein Barycenter","date":"2020-01-28","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."}