Language Tags Matter for Zero-Shot Neural Machine Translation

06/15/2021
by   Liwei Wu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/21/2017

Effective Strategies in Zero-Shot Neural Machine Translation

In this paper, we proposed two strategies which can be applied to a mult...
research
10/11/2021

Unsupervised Neural Machine Translation with Generative Language Models Only

We show how to derive state-of-the-art unsupervised neural machine trans...
research
02/01/2022

Examining Scaling and Transfer of Language Model Architectures for Machine Translation

Natural language understanding and generation models follow one of the t...
research
03/27/2023

Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses

In the field of Japanese-Chinese translation linguistics, the issue of c...
research
06/30/2022

Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations

Multilingual Neural Machine Translation (MNMT) enables one system to tra...
research
05/16/2023

Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation

This paper studies the impact of layer normalization (LayerNorm) on zero...
research
10/12/2020

Controllable Paraphrasing and Translation with a Syntactic Exemplar

Most prior work on exemplar-based syntactically controlled paraphrase ge...

Please sign up or login with your details

Forgot password? Click here to reset