Neural machine translation with source dependency representation

K Chen, R Wang, M Utiyama, L Liu… - Proceedings of the …, 2017 - aclanthology.org
K Chen, R Wang, M Utiyama, L Liu, A Tamura, E Sumita, T Zhao
Proceedings of the 2017 Conference on Empirical Methods in Natural …, 2017aclanthology.org
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 …
Abstract
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.
aclanthology.org