The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018
Miguel Graça, Yunsu Kim, Julian Schamper, Jiahui Geng, Hermann Ney
Abstract
This paper describes the unsupervised neural machine translation (NMT) systems of the RWTH Aachen University developed for the English ↔ German news translation task of the EMNLP 2018 Third Conference on Machine Translation (WMT 2018). Our work is based on iterative back-translation using a shared encoder-decoder NMT model. We extensively compare different vocabulary types, word embedding initialization schemes and optimization methods for our model. We also investigate gating and weight normalization for the word embedding layer.- Anthology ID:
- W18-6409
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 377–385
- Language:
- URL:
- https://aclanthology.org/W18-6409
- DOI:
- 10.18653/v1/W18-6409
- Cite (ACL):
- Miguel Graça, Yunsu Kim, Julian Schamper, Jiahui Geng, and Hermann Ney. 2018. The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 377–385, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018 (Graça et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W18-6409.pdf