arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1603.06111cs.CLcs.LGcs.NE
收藏

神经网络在NLP应用中的可移植性如何?

How Transferable are Neural Networks in NLP Applications?

Peking University(北京大学);Inveno Co., Ltd.(Inveno有限公司)

Lili Mou, Zhao Meng, Rui Yan, Ge Li, Yan Xu, Lu Zhang, Zhi Jin

摘要:

迁移学习旨在利用源领域中有价值的知识来帮助目标领域中的模型性能。这对神经网络尤其重要,因为神经网络很可能是过拟合的。在图像处理等领域,许多研究表明了基于神经网络的迁移学习的有效性。然而,对于神经NLP,现有的研究只是随意地应用了迁移学习,并且结论不一致。在本文中,我们进行了系统的案例研究,并提供了一个启发性的图片在自然语言处理的神经网络的可移植性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑