Abstract
The quality of Neural Machine Translation (NMT), as a data-driven approach, massively depends on quantity, quality, and relevance of the training dataset. Such approaches have achieved promising results for bilingually high-resource scenarios but are inadequate for low-resource conditions. This paper describes a round-trip training approach to bilingual low-resource NMT that takes advantage of monolingual datasets to address training data scarcity, thus augmenting translation quality. We conduct detailed experiments on Persian-Spanish as a bilingually low-resource scenario. Experimental results demonstrate that this competitive approach outperforms the baselines.- Anthology ID:
- R19-1003
- Volume:
- Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
- Month:
- September
- Year:
- 2019
- Address:
- Varna, Bulgaria
- Editors:
- Ruslan Mitkov, Galia Angelova
- Venue:
- RANLP
- SIG:
- Publisher:
- INCOMA Ltd.
- Note:
- Pages:
- 18–24
- Language:
- URL:
- https://aclanthology.org/R19-1003
- DOI:
- 10.26615/978-954-452-056-4_003
- Cite (ACL):
- Benyamin Ahmadnia and Bonnie Dorr. 2019. Bilingual Low-Resource Neural Machine Translation with Round-Tripping: The Case of Persian-Spanish. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 18–24, Varna, Bulgaria. INCOMA Ltd..
- Cite (Informal):
- Bilingual Low-Resource Neural Machine Translation with Round-Tripping: The Case of Persian-Spanish (Ahmadnia & Dorr, RANLP 2019)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/R19-1003.pdf