EMNLP 2021main87 citations

mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs

Zewen Chi, Li Dong, Shuming Ma, Shaohan Huang, Saksham Singhal, Xian-Ling Mao, Heyan Huang, Xia Song

Abstract

Multilingual T5 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 seven 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.

BibTeX
@inproceedings{chi-etal-2021-mt6,
    title = "m{T}6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs",
    author = "Chi, Zewen  and
      Dong, Li  and
      Ma, Shuming  and
      Huang, Shaohan  and
      Singhal, Saksham  and
      Mao, Xian-Ling  and
      Huang, Heyan  and
      Song, Xia  and
      Wei, Furu",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-main.125/",
    doi = "10.18653/v1/2021.emnlp-main.125",
    pages = "1671--1683"
}
mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs · EMNLP 2021