{"url":"/dataset/paws-x","name":"PAWS-X","full_name":"PAWS-X","description_markdown":"PAWS-X contains 23,659 human translated PAWS evaluation pairs and 296,406 machine translated training pairs in six typologically distinct languages: French, Spanish, German, Chinese, Japanese, and Korean. All translated pairs are sourced from examples in PAWS-Wiki.\r\n\r\nSource: [Google Research](https://github.com/google-research-datasets/paws/tree/master/pawsx)\r\nImage Source: [https://arxiv.org/pdf/1908.11828v1.pdf](https://arxiv.org/pdf/1908.11828v1.pdf)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/paws/tree/master/pawsx","introduced_date":"2019-08-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/paws-x-a-cross-lingual-adversarial-dataset","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","first_author":"Yinfei Yang","url":null},"license":{"name":"Custom (commercial)","url":"https://github.com/google-research-datasets/paws/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Cross-Lingual Transfer","url":"/task/cross-lingual-transfer","datasets_with_task":"/datasets/task/cross-lingual-transfer"},{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"},{"name":"FLUE","url":"/task/flue","datasets_with_task":"/datasets/task/flue"},{"name":"Cross-Lingual Paraphrase Identification","url":"/task/cross-lingual-paraphrase-identification","datasets_with_task":"/datasets/task/cross-lingual-paraphrase-identification"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Korean","url":"/datasets/language/korean"}],"variants":["PAWS-X","pawsx"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/paws-x","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/juletxara/pawsx_mt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/paws-x","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/paws_x_wiki","frameworks":["tf","jax"]},{"repo":"https://github.com/google-research-datasets/paws","url":"https://github.com/google-research-datasets/paws","frameworks":[]}],"num_papers_in_archive":172,"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."}