Multi-Task Neural Model for Agglutinative Language Translation

Yirong Pan, Xiao Li, Yating Yang, Rui Dong


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
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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.acl-srw.15.pdf
Video:
 http://slideslive.com/38928652