{"url":"/dataset/cos960","name":"COS960","full_name":null,"description_markdown":"A benchmark dataset with 960 pairs of Chinese wOrd Similarity, where all the words have two morphemes in three Part of Speech (POS) tags with their human annotated similarity rather than relatedness. \r\n\r\nSource: [COS960: A Chinese Word Similarity Dataset of 960 Word Pairs](/paper/190600247)","description_withheld":null,"homepage":"https://github.com/thunlp/COS960","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/190600247","title":"COS960: A Chinese Word Similarity Dataset of 960 Word Pairs","first_author":"Junjie Huang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"},{"name":"multi-word expression embedding","url":"/task/multi-word-expression-embedding","datasets_with_task":"/datasets/task/multi-word-expression-embedding"},{"name":"multi-word expression sememe prediction","url":"/task/multi-word-expression-sememe-prediction","datasets_with_task":"/datasets/task/multi-word-expression-sememe-prediction"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["COS960"],"data_loaders":[{"repo":"https://github.com/thunlp/COS960","url":"https://github.com/thunlp/COS960","frameworks":[]}],"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."}