{"url":"/dataset/polish-cdscorpus","name":"Polish CDSCorpus","full_name":null,"description_markdown":"Consists of 10K sentence pairs which are human-annotated for semantic relatedness and entailment. The dataset may be used for the evaluation of compositional distributional semantics models of Polish.\r\n\r\nSource: [Polish evaluation dataset for compositional distributional semantics models](/paper/polish-evaluation-dataset-for-compositional)","description_withheld":null,"homepage":"http://zil.ipipan.waw.pl/Scwad/CDSCorpus","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/polish-evaluation-dataset-for-compositional","title":"Polish evaluation dataset for compositional distributional semantics models","first_author":"Alina Wr{\\'o}blewska","url":null},"license":null,"modalities":[],"tasks":[{"name":"Semantic Composition","url":"/task/semantic-composition","datasets_with_task":"/datasets/task/semantic-composition"}],"languages":[{"name":"Polish","url":"/datasets/language/polish"}],"variants":["Polish CDSCorpus"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/community-datasets/cdsc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cdsc","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"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."}