Timezone: »

Data Diversification: A Simple Strategy For Neural Machine Translation
Xuan-Phi Nguyen · Shafiq Joty · Kui Wu · Ai Ti Aw

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #183

We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. It diversifies the training data by using the predictions of multiple forward and backward models and then merging them with the original dataset on which the final NMT model is trained. Our method is applicable to all NMT models. It does not require extra monolingual data like back-translation, nor does it add more computations and parameters like ensembles of models. Our method achieves state-of-the-art BLEU scores of 30.7 and 43.7 in the WMT'14 English-German and English-French translation tasks, respectively. It also substantially improves on 8 other translation tasks: 4 IWSLT tasks (English-German and English-French) and 4 low-resource translation tasks (English-Nepali and English-Sinhala). We demonstrate that our method is more effective than knowledge distillation and dual learning, it exhibits strong correlation with ensembles of models, and it trades perplexity off for better BLEU score.

Author Information

Xuan-Phi Nguyen (Nanyang Technological University)
Shafiq Joty (Nanyang Technological University)
Kui Wu (Institute for Infocomm Research, Singapore)
Ai Ti Aw (Institute for Infocomm Research)

More from the Same Authors