Multilingual T5 (mT5) pretrains a sequence-to-sequence model on massive monolingual texts, which has shown promising results on many cross-lingual tasks. In this paper, we improve multilingual text-to-text transfer Transformer with translation pairs (mT6). Specifically, we explore three cross-lingual text-to-text pre-training tasks, namely, machine translation, translation pair span corruption, and translation span corruption. In addition, we propose a partially non-autoregressive objective for text-to-text pre-training. We evaluate the methods on eight multilingual benchmark datasets, including sentence classification, named entity recognition, question answering, and abstractive summarization. Experimental results show that the proposed mT6 improves cross-lingual transferability over mT5.
@article{arxiv.2104.08692,
title = {MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs},
author = {Zewen Chi and Li Dong and Shuming Ma and Shaohan Huang Xian-Ling Mao and Heyan Huang and Furu Wei},
journal= {arXiv preprint arXiv:2104.08692},
year = {2021}
}