Generating Diverse Translation from Model Distribution with Dropout
Wu, Xuanfu, Feng, Yang, Shao, Chenze
–arXiv.org Artificial Intelligence
Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inference, the posterior model distribution can be approximated with a variational distribution, from which the final models for inference are sampled. We conducted experiments on Chinese-English and English-German translation tasks and the results shows that our method makes a better trade-off between diversity and accuracy.
arXiv.org Artificial Intelligence
Oct-16-2020
- Country:
- North America
- United States > Pennsylvania (0.04)
- Canada
- Ontario > Toronto (0.14)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Europe
- Czechia > Prague (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Asia > China
- North America
- Genre:
- Research Report > New Finding (0.35)