{"url":"/dataset/wikicaps","name":"WikiCaps","full_name":null,"description_markdown":"**WikiCaps** is a large-scale multilingual but non-parallel data set for multimodal machine translation and retrieval. The image-caption data was extracted from Wikimedia Commons and is thus a representative of the collection of largely available non-descriptive image-caption pairs in the web. The current version of the dataset contains 3,816,940 images with 3,825,132 English captions and additional 1,000 image-caption pairs in German, French, and Russian together with their English counterparts.\r\n\r\nSource: [WikiCaps](https://www.cl.uni-heidelberg.de/statnlpgroup/wikicaps/)","description_withheld":null,"homepage":"https://www.cl.uni-heidelberg.de/statnlpgroup/wikicaps/","introduced_date":"2018-03-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-dataset-and-reranking-method-for-multimodal","title":"A Dataset and Reranking Method for Multimodal MT of User-Generated Image Captions","first_author":"Shigehiko Schamoni","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"German","url":"/datasets/language/german"},{"name":"Russian","url":"/datasets/language/russian"}],"variants":["WikiCaps"],"data_loaders":[],"num_papers_in_archive":2,"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."}