Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machine Translation
This work addresses translation accuracy for English-Chinese tasks, representing an incremental improvement over prior attention-based and tree-based models.
The paper tackled the problem of improving neural machine translation by enhancing source-side hierarchical representations with a bidirectional tree-based encoder and a weighted attention mechanism, resulting in significant performance gains over existing models in English-Chinese translation tasks.
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.