{"url":"/dataset/japanese-word-similarity","name":"Japanese Word Similarity","full_name":null,"description_markdown":"This dataset contains information about Japanese word similarity including rare words. The dataset is constructed following the Stanford Rare Word Similarity Dataset. 10 annotators annotated word pairs with 11 levels of similarity.\n\nSource: [https://github.com/tmu-nlp/JapaneseWordSimilarityDataset](https://github.com/tmu-nlp/JapaneseWordSimilarityDataset)","description_withheld":null,"homepage":"https://github.com/tmu-nlp/JapaneseWordSimilarityDataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/construction-of-a-japanese-word-similarity","title":"Construction of a Japanese Word Similarity Dataset","first_author":"Yuya Sakaizawa","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["Japanese Word Similarity"],"data_loaders":[{"repo":"https://github.com/tmu-nlp/JapaneseWordSimilarityDataset","url":"https://github.com/tmu-nlp/JapaneseWordSimilarityDataset","frameworks":[]}],"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":"2026-09-25T09:33:49+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."}