Self-Learning for Zero Shot Neural Machine Translation

03/10/2021
by   Surafel M. Lakew, et al.
19

Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance. This work proposes a novel zero-shot NMT modeling approach that learns without the now-standard assumption of a pivot language sharing parallel data with the zero-shot source and target languages. Our approach is based on three stages: initialization from any pre-trained NMT model observing at least the target language, augmentation of source sides leveraging target monolingual data, and learning to optimize the initial model to the zero-shot pair, where the latter two constitute a self-learning cycle. Empirical findings involving four diverse (in terms of a language family, script and relatedness) zero-shot pairs show the effectiveness of our approach with up to +5.93 BLEU improvement against a supervised bilingual baseline. Compared to unsupervised NMT, consistent improvements are observed even in a domain-mismatch setting, attesting to the usability of our method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/25/2018

Zero-Shot Dual Machine Translation

Neural Machine Translation (NMT) systems rely on large amounts of parall...
research
05/25/2023

MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation

Efficient utilisation of both intra- and extra-textual context remains o...
research
09/28/2019

The Source-Target Domain Mismatch Problem in Machine Translation

While we live in an increasingly interconnected world, different places ...
research
05/12/2022

Controlling Formality in Low-Resource NMT with Domain Adaptation and Re-Ranking: SLT-CDT-UoS at IWSLT2022

This paper describes the SLT-CDT-UoS group's submission to the first Spe...
research
10/02/2021

Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages

Although the multilingual Neural Machine Translation(NMT), which extends...
research
08/26/2018

Contextual Parameter Generation for Universal Neural Machine Translation

We propose a simple modification to existing neural machine translation ...
research
08/11/2022

Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation

This paper proposes a simple yet effective method to improve direct (X-t...

Please sign up or login with your details

Forgot password? Click here to reset