Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary

Surafel M. Lakew, Aliia Erofeeva, Matteo Negri, Marcello Federico, Marco Turchi


Abstract
We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting its vocabulary as long as new data become available (i.e., introducing new vocabulary items if they are not included in the initial model). The parameter transfer mechanism is evaluated in two scenarios: i) to adapt a trained single language NMT system to work with a new language pair and ii) to continuously add new language pairs to grow to a multilingual NMT system. In both the scenarios our goal is to improve the translation performance, while minimizing the training convergence time. Preliminary experiments spanning five languages with different training data sizes (i.e., 5k and 50k parallel sentences) show a significant performance gain ranging from +3.85 up to +13.63 BLEU in different language directions. Moreover, when compared with training an NMT model from scratch, our transfer-learning approach allows us to reach higher performance after training up to 4% of the total training steps.
Anthology ID:
2018.iwslt-1.8
Volume:
Proceedings of the 15th International Conference on Spoken Language Translation
Month:
October 29-30
Year:
2018
Address:
Brussels
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
International Conference on Spoken Language Translation
Note:
Pages:
54–61
Language:
URL:
https://aclanthology.org/2018.iwslt-1.8
DOI:
Bibkey:
Cite (ACL):
Surafel M. Lakew, Aliia Erofeeva, Matteo Negri, Marcello Federico, and Marco Turchi. 2018. Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 54–61, Brussels. International Conference on Spoken Language Translation.
Cite (Informal):
Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary (Lakew et al., IWSLT 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2018.iwslt-1.8.pdf
Code
 additional community code