{"url":"/dataset/wikisem500","name":"WikiSem500","full_name":null,"description_markdown":"The **WikiSem500** dataset contains around 500 per-language cluster groups for English, Spanish, German, Chinese, and Japanese (a total of 13,314 test cases).\n\nSource: [https://arxiv.org/abs/1611.01547](https://arxiv.org/abs/1611.01547)","description_withheld":null,"homepage":"https://github.com/belph/wiki-sem-500","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/automated-generation-of-multilingual-clusters","title":"Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations","first_author":"Philip Blair","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Outlier Detection","url":"/task/outlier-detection","datasets_with_task":"/datasets/task/outlier-detection"},{"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"},{"name":"German","url":"/datasets/language/german"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["WikiSem500"],"data_loaders":[{"repo":"https://github.com/belph/wiki-sem-500","url":"https://github.com/belph/wiki-sem-500","frameworks":[]}],"num_papers_in_archive":4,"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."}