Abstract
Neural machine translation (NMT) has achieved impressive performance recently by using large-scale parallel corpora. However, it struggles in the low-resource and morphologically-rich scenarios of agglutinative language translation task. Inspired by the finding that monolingual data can greatly improve the NMT performance, we propose a multi-task neural model that jointly learns to perform bi-directional translation and agglutinative language stemming. Our approach employs the shared encoder and decoder to train a single model without changing the standard NMT architecture but instead adding a token before each source-side sentence to specify the desired target outputs of the two different tasks. Experimental results on Turkish-English and Uyghur-Chinese show that our proposed approach can significantly improve the translation performance on agglutinative languages by using a small amount of monolingual data.- Anthology ID:
- 2020.acl-srw.15
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Shruti Rijhwani, Jiangming Liu, Yizhong Wang, Rotem Dror
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 103–110
- Language:
- URL:
- https://aclanthology.org/2020.acl-srw.15
- DOI:
- 10.18653/v1/2020.acl-srw.15
- Cite (ACL):
- Yirong Pan, Xiao Li, Yating Yang, and Rui Dong. 2020. Multi-Task Neural Model for Agglutinative Language Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 103–110, Online. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Task Neural Model for Agglutinative Language Translation (Pan et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2020.acl-srw.15.pdf