Abstract
While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. Based on the assumption, our method is able to train a source-to-target NMT model (“student”) without parallel corpora available guided by an existing pivot-to-target NMT model (“teacher”) on a source-pivot parallel corpus. Experimental results show that the proposed method significantly improves over a baseline pivot-based model by +3.0 BLEU points across various language pairs.- Anthology ID:
- P17-1176
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1925–1935
- Language:
- URL:
- https://aclanthology.org/P17-1176
- DOI:
- 10.18653/v1/P17-1176
- Cite (ACL):
- Yun Chen, Yang Liu, Yong Cheng, and Victor O.K. Li. 2017. A Teacher-Student Framework for Zero-Resource Neural Machine Translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1925–1935, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- A Teacher-Student Framework for Zero-Resource Neural Machine Translation (Chen et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/naacl24-info/P17-1176.pdf