{"url":"/dataset/mmid","name":"MMID","full_name":"Massively Multilingual Image Dataset","description_markdown":"A large-scale multilingual corpus of images, each labeled with the word it represents. The dataset includes approximately 10,000 words in each of 100 languages.\r\n\r\nSource: [Learning Translations via Images with a Massively Multilingual Image Dataset](/paper/learning-translations-via-images-with-a)","description_withheld":null,"homepage":"http://multilingual-images.org/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-translations-via-images-with-a","title":"Learning Translations via Images with a Massively Multilingual Image Dataset","first_author":"John Hewitt","url":null},"license":null,"modalities":[],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"}],"languages":[],"variants":["MMID"],"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":"2026-09-24T18:15:14+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."}