Enriching the Transformer with Linguistic Factors for Low-Resource Machine Translation

Jordi Armengol-Estapé, Marta R. Costa-jussà, Carlos Escolano


Abstract
Introducing factors, that is to say, word features such as linguistic information referring to the source tokens, is known to improve the results of neural machine translation systems in certain settings, typically in recurrent architectures. This study proposes enhancing the current state-of-the-art neural machine translation architecture, the Transformer, so that it allows to introduce external knowledge. In particular, our proposed modification, the Factored Transformer, uses linguistic factors that insert additional knowledge into the machine translation system. Apart from using different kinds of features, we study the effect of different architectural configurations. Specifically, we analyze the performance of combining words and features at the embedding level or at the encoder level, and we experiment with two different combination strategies. With the best-found configuration, we show improvements of 0.8 BLEU over the baseline Transformer in the IWSLT German-to-English task. Moreover, we experiment with the more challenging FLoRes English-to-Nepali benchmark, which includes both extremely low-resourced and very distant languages, and obtain an improvement of 1.2 BLEU
Anthology ID:
2021.ranlp-1.9
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
73–78
Language:
URL:
https://aclanthology.org/2021.ranlp-1.9
DOI:
Bibkey:
Cite (ACL):
Jordi Armengol-Estapé, Marta R. Costa-jussà, and Carlos Escolano. 2021. Enriching the Transformer with Linguistic Factors for Low-Resource Machine Translation. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 73–78, Held Online. INCOMA Ltd..
Cite (Informal):
Enriching the Transformer with Linguistic Factors for Low-Resource Machine Translation (Armengol-Estapé et al., RANLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.ranlp-1.9.pdf