Language Tags Matter for Zero-Shot Neural Machine Translation

Abstract

Multilingual Neural Machine Translation (MNMT) has aroused widespread interest due to its efficiency. An exciting advantage of MNMT models is that they could also translate between unsupervised (zero-shot) language directions. Language tag (LT) strategies are often adopted to indicate the translation directions in MNMT. In this paper, we demonstrate that the LTs are not only indicators for translation directions but also crucial to zero-shot translation qualities. Unfortunately, previous work tends to ignore the importance of LT strategies. We demonstrate that a proper LT strategy could enhance the consistency of semantic representations and alleviate the off-target issue in zero-shot directions. Experimental results show that by ignoring the source language tag (SLT) and adding the target language tag (TLT) to the encoder, the zero-shot translations could achieve a +8 BLEU score difference over other LT strategies in IWSLT17, Europarl, TED talks translation tasks.

7 pages, 3 figures, Accepted by the Findings of ACL2021

References in corpus (7)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Multilingual Denoising Pre-training for Neural Machine Translation
• Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
• A Comprehensive Survey of Multilingual Neural Machine Translation