%0 Conference Proceedings %T Neural Machine Translation with Source Dependency Representation %A Chen, Kehai %A Wang, Rui %A Utiyama, Masao %A Liu, Lemao %A Tamura, Akihiro %A Sumita, Eiichiro %A Zhao, Tiejun %Y Palmer, Martha %Y Hwa, Rebecca %Y Riedel, Sebastian %S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing %D 2017 %8 September %I Association for Computational Linguistics %C Copenhagen, Denmark %F chen-etal-2017-neural %X Source dependency information has been successfully introduced into statistical machine translation. However, there are only a few preliminary attempts for Neural Machine Translation (NMT), such as concatenating representations of source word and its dependency label together. In this paper, we propose a novel NMT with source dependency representation to improve translation performance of NMT, especially long sentences. Empirical results on NIST Chinese-to-English translation task show that our method achieves 1.6 BLEU improvements on average over a strong NMT system. %R 10.18653/v1/D17-1304 %U https://aclanthology.org/D17-1304 %U https://doi.org/10.18653/v1/D17-1304 %P 2846-2852