Xue, LintingConstant, NoahRoberts, AdamKale, MihirAl‑Rfou, RamiSiddhant, AdityaBarua, AdityaRaffel, Colin2025-06-022025-06-022025-06-022020-10-22https://arxiv.org/abs/2010.11934http://data.inu.ac.kr/handle/123456789/1960.2영어 위주의 T5를 101개 언어로 확장한 mT5 모델을 제안하며, 다국어 벤치마크에서 우수한 결과를 보여줍니다. 특히 제로샷 번역 시 특정 언어로 전이되는 문제를 완화한 전략도 포함됩니다 ©2020 Google ResearchThe recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent "accidental translation" in the zero-shot setting, where a generative model chooses to (partially) translate its prediction into the wrong language. All of the code and model checkpoints used in this work are publicly available.en-USmT5Multilingual NLPText-to-TextTransfer LearningZero-shotArticle