TY - GEN
T1 - NTT Neural Machine Translation Systems at WAT 2017
AU - Morishita, Makoto
AU - Suzuki, Jun
AU - Nagata, Masaaki
N1 - Publisher Copyright:
© 2017 AFNLP
PY - 2017
Y1 - 2017
N2 - In this year, we participated in four translation subtasks at WAT 2017. Our model structure is quite simple but we used it with well-tuned hyper-parameters, leading to a significant improvement compared to the previous state-of-the-art system. We also tried to make use of the unreliable part of the provided parallel corpus by back-translating and making a synthetic corpus. Our submitted system achieved the new state-of-the-art performance in terms of the BLEU score, as well as human evaluation.
AB - In this year, we participated in four translation subtasks at WAT 2017. Our model structure is quite simple but we used it with well-tuned hyper-parameters, leading to a significant improvement compared to the previous state-of-the-art system. We also tried to make use of the unreliable part of the provided parallel corpus by back-translating and making a synthetic corpus. Our submitted system achieved the new state-of-the-art performance in terms of the BLEU score, as well as human evaluation.
UR - http://www.scopus.com/inward/record.url?scp=85095077586&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85095077586&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85095077586
T3 - IJCNLP 2017 - 4th Workshop on Asian Translation, WMT 2017 - Proceedings of the Workshop
SP - 89
EP - 94
BT - IJCNLP 2017 - 4th Workshop on Asian Translation, WMT 2017 - Proceedings of the Workshop
PB - Association for Computational Linguistics (ACL)
T2 - IJCNLP 2017 4th Workshop on Asian Translation, WMT 2017
Y2 - 27 November 2017 through 1 December 2017
ER -