Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation

Baosong Yang, Derek F. Wong, Tong Xiao, Lidia S. Chao, Jingbo Zhu


Abstract
This paper proposes a hierarchical attentional neural translation model which focuses on enhancing source-side hierarchical representations by covering both local and global semantic information using a bidirectional tree-based encoder. To maximize the predictive likelihood of target words, a weighted variant of an attention mechanism is used to balance the attentive information between lexical and phrase vectors. Using a tree-based rare word encoding, the proposed model is extended to sub-word level to alleviate the out-of-vocabulary (OOV) problem. Empirical results reveal that the proposed model significantly outperforms sequence-to-sequence attention-based and tree-based neural translation models in English-Chinese translation tasks.
Anthology ID:
D17-1150
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1432–1441
Language:
URL:
https://www.aclweb.org/anthology/D17-1150
DOI:
10.18653/v1/D17-1150
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1150.pdf