Exploring diversity in back translation for low-resource machine translation

Laurie Burchell, Alexandra Birch, Kenneth Heafield


Abstract
Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the ‘diversity’ of the generated translations. We argue that the definitions and metrics used to quantify ‘diversity’ in previous work have been insufficient. This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity and carry out empirical analysis into the effect of these types of diversity on final neural machine translation model performance for low-resource English↔Turkish and mid-resource English↔Icelandic. Our findings show that generating back translation using nucleus sampling results in higher final model performance, and that this method of generation has high levels of both lexical and syntactic diversity. We also find evidence that lexical diversity is more important than syntactic for back translation performance.
Anthology ID:
2022.deeplo-1.8
Volume:
Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
Month:
July
Year:
2022
Address:
Hybrid
Editors:
Colin Cherry, Angela Fan, George Foster, Gholamreza (Reza) Haffari, Shahram Khadivi, Nanyun (Violet) Peng, Xiang Ren, Ehsan Shareghi, Swabha Swayamdipta
Venue:
DeepLo
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
67–79
Language:
URL:
https://aclanthology.org/2022.deeplo-1.8
DOI:
10.18653/v1/2022.deeplo-1.8
Bibkey:
Cite (ACL):
Laurie Burchell, Alexandra Birch, and Kenneth Heafield. 2022. Exploring diversity in back translation for low-resource machine translation. In Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing, pages 67–79, Hybrid. Association for Computational Linguistics.
Cite (Informal):
Exploring diversity in back translation for low-resource machine translation (Burchell et al., DeepLo 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.deeplo-1.8.pdf
Video:
 https://aclanthology.org/2022.deeplo-1.8.mp4
Code
 laurieburchell/exploring-diversity-bt