Open Access
ARTICLE
Improve Neural Machine Translation by Building Word Vector with Part of Speech
Jinyingming Zhang1 , Jin Liu1, *, Xinyue Lin1
1 College of Information Engineering, Shanghai Maritime University, Shanghai, China.
* Corresponding Author: Jin Liu. Email: .
Journal on Artificial Intelligence 2020, 2(2), 79-88. https://doi.org/10.32604/jai.2020.010476
Received 06 March 2020; Accepted 06 June 2020; Issue published 15 July 2020
Abstract
Neural Machine Translation (NMT) based system is an important technology
for translation applications. However, there is plenty of rooms for the improvement of
NMT. In the process of NMT, traditional word vector cannot distinguish the same words
under different parts of speech (POS). Aiming to alleviate this problem, this paper proposed
a new word vector training method based on POS feature. It can efficiently improve the
quality of translation by adding POS feature to the training process of word vectors. In the
experiments, we conducted extensive experiments to evaluate our methods. The
experimental result shows that the proposed method is beneficial to improve the quality of
translation from English into Chinese.
Keywords
Cite This Article
J. Zhang, ,. Jin Liu and X. Lin, "Improve neural machine translation by building word vector with part of speech,"
Journal on Artificial Intelligence, vol. 2, no.2, pp. 79–88, 2020.