XNLI

Cross-lingual Natural Language Inference

The Cross-lingual Natural Language Inference (XNLI) corpus is the extension of the Multi-Genre NLI (MultiNLI) corpus to 15 languages. The dataset was created by manually translating the validation and test sets of MultiNLI into each of those 15 languages. The English training set was machine translated for all languages. The dataset is composed of 122k train, 2490 validation and 5010 test examples. Source: CamemBERT: a Tasty French Language Model Image Source: https://github.com/facebookresearch/XNLI

Texts FrenchSpanishGermanChineseMultilingualRussianArabicBulgarianHindiThaiTurkishUrduVietnameseGreekSwahili

벤치마크

Natural Language Inference on XNLI French 결과 6개

Cross-Lingual Natural Language Inference on XNLI 결과 5개

Cross-Lingual Natural Language Inference on XNLI Zero-Shot English-to-German 결과 4개

Cross-Lingual Natural Language Inference on XNLI Zero-Shot English-to-Spanish 결과 4개

Cross-Lingual Natural Language Inference on XNLI Zero-Shot English-to-French 결과 3개

Natural Language Inference on XNLI Chinese 결과 3개

Natural Language Inference on XNLI Chinese Dev 결과 3개