Datasets › PAWS-X

PAWS-X

Introduced by Yinfei Yang et al. in PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification30 Aug 2019 archive 2025-07-28

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.

Source: Google Research Image Source: https://arxiv.org/pdf/1908.11828v1.pdf

Homepage JSON

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 172 papers for it but never published that list.

Dataset loaders archive 2025-07-28

huggingface.co/datasets/paws-x huggingface/datasetstfpytorchjax

huggingface.co/datasets/juletxara/pawsx_mt huggingface/datasetstfpytorchjax

huggingface.co/datasets/google-research-datasets/paws-x huggingface/datasetstfpytorchjax

www.tensorflow.org/datasets/catalog/paws_x_wiki tensorflow/datasetstfjax

google-research-datasets/paws

5 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Language Modelling Cross-Lingual Transfer Paraphrase Identification FLUE Cross-Lingual Paraphrase Identification

License archive 2025-07-28

Custom (commercial)

Modalities archive 2025-07-28

Texts

Languages archive 2025-07-28

English French Spanish German Chinese Japanese Korean

Variants archive 2025-07-28

PAWS-X
pawsx

2 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections