DOCmT5: Document-Level Pretraining of Multilingual Language Models
Chia-Hsuan Lee, Aditya Siddhant, Viresh Ratnakar, Melvin Johnson · Findings of the Association for Computational Linguistics: NAACL 2022 · 2022
In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents.While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pretrained model that can understand and generate long documents.We propose a simple and effective pretraining objective -Document reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated.DrMT brings consistent improvements over strong baselines on a variety of document-level generation tasks, including over 12 BLEU points for seen-languagepair document-level MT, over 7 BLEU points for unseen-language-pair document-level MT and over 3 ROUGE-1 points for seen-languagepair cross-lingual summarization.We achieve state-of-the-art (SOTA) on WMT20 De-En and IWSLT15 Zh-En document translation tasks.We also conduct extensive analysis on various factors for document pretraining, including (1) the effects of pretraining data quality and (2) the effects of combining mono-lingual and crosslingual pretraining.We plan to make our model checkpoints publicly available.