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.
@article{arxiv.1707.05114,
title = {Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machine Translation},
author = {Baosong Yang and Derek F. Wong and Tong Xiao and Lidia S. Chao and Jingbo Zhu},
journal= {arXiv preprint arXiv:1707.05114},
year = {2017}
}