TY - GEN
T1 - NYU-MILA Neural Machine Translation Systems for WMT'16
AU - Chung, Junyoung
AU - Cho, Kyunghyun
AU - Bengio, Yoshua
N1 - Funding Information:
The authors would like to thank the developers of Theano (Team et al., 2016). We acknowledge the support of the following agencies for research funding and computing support: NSERC, Calcul Québec, Compute Canada, the Canada Research Chairs, CIFAR and Samsung. KC thanks the support by Facebook, Google (Google Faculty Award 2016) and NVIDIA (GPU Center of Excellence 2015-2016). JC thanks Orhan Firat for his constructive feedbacks.
Publisher Copyright:
© 2016 Association for Computational Linguistics.
PY - 2016
Y1 - 2016
N2 - We describe the neural machine translation system of New York University (NYU) and University of Montreal (MILA) for the translation tasks of WMT'16. The main goal of NYU-MILA submission to WMT'16 is to evaluate a new character-level decoding approach in neural machine translation on various language pairs. The proposed neural machine translation system is an attention-based encoder-decoder with a subword-level encoder and a character-level decoder. The decoder of the neural machine translation system does not require explicit segmentation, when characters are used as tokens. The character-level decoding approach provides benefits especially when translating a source language into other morphologically rich languages.
AB - We describe the neural machine translation system of New York University (NYU) and University of Montreal (MILA) for the translation tasks of WMT'16. The main goal of NYU-MILA submission to WMT'16 is to evaluate a new character-level decoding approach in neural machine translation on various language pairs. The proposed neural machine translation system is an attention-based encoder-decoder with a subword-level encoder and a character-level decoder. The decoder of the neural machine translation system does not require explicit segmentation, when characters are used as tokens. The character-level decoding approach provides benefits especially when translating a source language into other morphologically rich languages.
UR - http://www.scopus.com/inward/record.url?scp=85123203798&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123203798&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85123203798
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 268
EP - 271
BT - Shared Task Papers
PB - Association for Computational Linguistics (ACL)
T2 - 1st Conference on Machine Translation, WMT 2016, held at the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Y2 - 7 August 2016 through 12 August 2016
ER -