{"url":"/dataset/ocnli","name":"OCNLI","full_name":"Original Chinese Natural Language Inference","description_markdown":"OCNLI stands for Original Chinese Natural Language Inference. It is corpus for Chinese Natural Language Inference, collected following closely the procedures of MNLI, but with enhanced strategies aiming for more challenging inference pairs. No human/machine translation is used in creating the dataset, and thus the Chinese texts are original and not translated.\r\n\r\nOCNLI has roughly 50k pairs for training, 3k for development and 3k for test. Only the test data is released but not its labels.\r\n\r\nOCNLI is part of the CLUE benchmark.\r\n\r\nSource: [OCNLI](https://github.com/CLUEbenchmark/OCNLI)","description_withheld":null,"homepage":"https://github.com/CLUEbenchmark/OCNLI","introduced_date":"2020-10-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/ocnli-original-chinese-natural-language","title":"OCNLI: Original Chinese Natural Language Inference","first_author":"Hai Hu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Natural Language Inference (Zero-Shot)","url":"/task/natural-language-inference-zero-shot","datasets_with_task":"/datasets/task/natural-language-inference-zero-shot"},{"name":"Natural Language Inference (One-Shot)","url":"/task/natural-language-inference-one-shot","datasets_with_task":"/datasets/task/natural-language-inference-one-shot"},{"name":"Natural Language Inference (Few-Shot)","url":"/task/natural-language-inference-few-shot","datasets_with_task":"/datasets/task/natural-language-inference-few-shot"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["OCNLI"],"data_loaders":[{"repo":"https://github.com/CLUEbenchmark/OCNLI","url":"https://github.com/CLUEbenchmark/OCNLI","frameworks":["tf"]}],"num_papers_in_archive":44,"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."}