Can I read Multilingual Denoising Pre-training for Neural Machine Translation on EtoBox?

Multilingual Denoising Pre-training for Neural Machine Translation by Liu, Yinhan; Gu, Jiatao; Goyal, Naman; Li, Xian; Edunov, Sergey; Ghazvininejad, Marjan; Lewis, Mike; Zettlemoyer, Luke is a scholarly article available to read on EtoBox.

What is Multilingual Denoising Pre-training for Neural Machine Translation about?

This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present mBART -- a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective. mBART is one of the first methods for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, while previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text. Pre-training a complete model allows it to be directly fine tuned for supervised (both sentence-level and document-level) and unsupervised machine translation, with no task-specific modifications. We demonstrate that adding mBART initialization produces performance gains in all but the highest-resource settings, including up to 12 BLEU points for low resource MT and over 5 BLEU points for many document-level and unsupervised models. We also show it also enables new types of transfer to language pairs with no bi-text or that were not in the pre-training corpus, and present extensive analysis of which factors contribute the most to ef

Author

Liu, Yinhan; Gu, Jiatao; Goyal, Naman; Li, Xian; Edunov, Sergey; Ghazvininejad, Marjan; Lewis, Mike; Zettlemoyer, Luke

Published

2020

Language

EN