English

Generating Diverse Translation by Manipulating Multi-Head Attention

Computation and Language 2019-11-22 v1

Abstract

Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the final decoder layer align to different word translation candidates. We empirically verify this discovery and propose a method to generate diverse translations by manipulating heads. Furthermore, we make use of these diverse translations with the back-translation technique for better data augmentation. Experiment results show that our method generates diverse translations without severe drop in translation quality. Experiments also show that back-translation with these diverse translations could bring significant improvement on performance on translation tasks. An auxiliary experiment of conversation response generation task proves the effect of diversity as well.

Keywords

Cite

@article{arxiv.1911.09333,
  title  = {Generating Diverse Translation by Manipulating Multi-Head Attention},
  author = {Zewei Sun and Shujian Huang and Hao-Ran Wei and Xin-yu Dai and Jiajun Chen},
  journal= {arXiv preprint arXiv:1911.09333},
  year   = {2019}
}

Comments

Accepted by AAAI 2020

R2 v1 2026-06-23T12:23:06.106Z