How Transferable are Neural Networks in NLP Applications?

Lili Mou1, Zhao Meng2, Rui Yan3, Ge Li1, Yan Xu4, Lu Zhang1, Zhi Jin1
1Peking University, 2Software Institute, Peking University, Beijing 100871, P. R. China, 3Baidu Inc., 4PKU


Abstract

Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain. It is particularly important to neural networks, which are very likely to be overfitting. In some fields like image processing, many studies have shown the effectiveness of neural network-based transfer learning. For neural NLP, however, existing studies have only casually applied transfer learning, and conclusions are inconsistent. In this paper, we conduct systematic case studies and provide an illuminating picture on the transferability of neural networks in NLP.