Addressing Troublesome Words in Neural Machine Translation

Yang Zhao, Jiajun Zhang, Zhongjun He, Chengqing Zong, Hua Wu


Abstract
One of the weaknesses of Neural Machine Translation (NMT) is in handling lowfrequency and ambiguous words, which we refer as troublesome words. To address this problem, we propose a novel memoryenhanced NMT method. First, we investigate different strategies to define and detect the troublesome words. Then, a contextual memory is constructed to memorize which target words should be produced in what situations. Finally, we design a hybrid model to dynamically access the contextual memory so as to correctly translate the troublesome words. The extensive experiments on Chinese-to-English and English-to-German translation tasks demonstrate that our method significantly outperforms the strong baseline models in translation quality, especially in handling troublesome words.
Anthology ID:
D18-1036
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
391–400
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/D18-1036/
DOI:
10.18653/v1/D18-1036
Bibkey:
Cite (ACL):
Yang Zhao, Jiajun Zhang, Zhongjun He, Chengqing Zong, and Hua Wu. 2018. Addressing Troublesome Words in Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 391–400, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Addressing Troublesome Words in Neural Machine Translation (Zhao et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/D18-1036.pdf