%0 Conference Proceedings %T NTT Neural Machine Translation Systems at WAT 2019 %A Morishita, Makoto %A Suzuki, Jun %A Nagata, Masaaki %Y Nakazawa, Toshiaki %Y Ding, Chenchen %Y Dabre, Raj %Y Kunchukuttan, Anoop %Y Doi, Nobushige %Y Oda, Yusuke %Y Bojar, Ondřej %Y Parida, Shantipriya %Y Goto, Isao %Y Mino, Hidaya %S Proceedings of the 6th Workshop on Asian Translation %D 2019 %8 November %I Association for Computational Linguistics %C Hong Kong, China %F morishita-etal-2019-ntt %X In this paper, we describe our systems that were submitted to the translation shared tasks at WAT 2019. This year, we participated in two distinct types of subtasks, a scientific paper subtask and a timely disclosure subtask, where we only considered English-to-Japanese and Japanese-to-English translation directions. We submitted two systems (En-Ja and Ja-En) for the scientific paper subtask and two systems (Ja-En, texts, items) for the timely disclosure subtask. Three of our four systems obtained the best human evaluation performances. We also confirmed that our new additional web-crawled parallel corpus improves the performance in unconstrained settings. %R 10.18653/v1/D19-5211 %U https://aclanthology.org/D19-5211 %U https://doi.org/10.18653/v1/D19-5211 %P 99-105