Projects per year
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 3rd Workshop on Deep Learning for Low-Resource NLP |
Editors | Colin Cherry, Angela Fan, George Foster, Gholamreza (Reza) Haffari, Shahram Khadivi, Nanyun (Violet) Peng, Xiang Ren, Ehsan Shareghi, Swabha Swayamdipta |
Place of Publication | Stroudsburg, PA, USA |
Publisher | Association for Computational Linguistics |
Pages | 67-79 |
Number of pages | 13 |
ISBN (Electronic) | 9781955917971 |
DOIs | |
Publication status | Published - 14 Jul 2022 |
Event | The 3rd Deep Learning for Low-Resource NLP Workshop - Seattle, United States Duration: 14 Jul 2022 → 14 Jul 2022 Conference number: 3 https://sites.google.com/view/deeplo-2022/home |
Workshop
Workshop | The 3rd Deep Learning for Low-Resource NLP Workshop |
---|---|
Abbreviated title | DeepLo 2022 |
Country/Territory | United States |
City | Seattle |
Period | 14/07/22 → 14/07/22 |
Internet address |
Fingerprint
Dive into the research topics of 'Exploring diversity in back translation for low-resource machine translation'. Together they form a unique fingerprint.Projects
- 2 Finished
-
Global Under-Resourced MEdia Translation
Birch-Mayne, A. (Principal Investigator) & Haddow, B. (Co-investigator)
1/01/19 → 30/06/22
Project: Research
-
MTStretch: Low-resource Machine Translation
Birch-Mayne, A. (Principal Investigator)
29/06/18 → 28/12/21
Project: Research