Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
Preprint
Abstract
The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised directions to zero-shot directions, the multilingual NMT model is expected to learn universal representations across different languages. This paper introduces a cross-lingual consistency regularization, CrossConST, to bridge the representation gap among different languages and boost zero-shot translation performance. The theoretical analysis shows that CrossConST implicitly maximizes the probability distribution for zero-shot translation, and the experimental results on both low-resource and high-resource benchmarks show that CrossConST consistently improves the translation performance. The experimental analysis also proves that CrossConST could close the sentence representation gap and better align the representation space. Given the universality and simplicity of CrossConST, we believe it can serve as a strong baseline for future multilingual NMT research.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Improving Multilingual Translation by Representation and Gradient Regularization2021
- Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders2021
- Improving Zero-Shot Translation by Disentangling Positional Information2021
- Language Tags Matter for Zero-Shot Neural Machine Translation2021
- Multilingual Agreement for Multilingual Neural Machine Translation2021
- Contrastive Learning for Many-to-many Multilingual Neural Machine Translation2021
- Cross-Lingual Pre-Training Based Transfer for Zero-Shot Neural Machine TranslationProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information2020
- Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation2020
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot TranslationTransactions of the Association for Computational Linguistics, 2017