Indexed on: 08 Nov '16Published on: 08 Nov '16Published in: arXiv - Computer Science - Computation and Language
Sequence to sequence models are successful tools for supervised sequence learning tasks, such as machine translation. Despite their success, these models still require much labeled data and it is unclear how to improve them using unlabeled data, which is much less expensive to obtain. In this paper, we present simple changes that lead to a significant improvement in the accuracy of seq2seq models when the labeled set is small. Our method intializes the encoder and decoder of the seq2seq model with the trained weights of two language models, and then all weights are jointly fine-tuned with labeled data. An additional language modeling loss can be used to regularize the model during fine-tuning. We apply this method to low-resource tasks in machine translation and abstractive summarization and find that it significantly improves the subsequent supervised models. Our main finding is that the pretraining accelerates training and improves generalization of seq2seq models, achieving state-of-the-art results on the WMT English$\rightarrow$German task. Our model obtains an improvement of 1.3 BLEU from the previous best models on both WMT'14 and WMT'15 English$\rightarrow$German. Our ablation study shows that pretraining helps seq2seq models in different ways depending on the nature of the task: translation benefits from the improved generalization whereas summarization benefits from the improved optimization.