@inproceedings{wang2018dual,
author = {Wang, Yijun and Xia, Yingce and Zhao, Li and Bian, Jiang and Qin, Tao and liu, GuiQuan and Liu, Tie-Yan},
title = {Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization},
booktitle = {Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence},
year = {2018},
month = {February},
abstract = {Neural machine translation (NMT) heavily relies on parallel bilingual data for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection to learn from and regularize the training of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the dual translation model (target-to-source translation) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. That is, we transfer the knowledge contained in the dual model to boost the training of the primal model (source-to-target translation), and we call such an approach dual transfer learning. Experiment results on English→French and German→English tasks demonstrate that dual transfer learning achieves significant improvement over several strong baselines and obtains new state-of-the-art results.},
url = {http://approjects.co.za/?big=en-us/research/publication/dual-transfer-learning-neural-machine-translation-marginal-distribution-regularization/},
edition = {AAAI 2018},
}