arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.01009cs.CLcs.NE
收藏

语言RNN的激活正则化研究

Revisiting Activation Regularization for Language RNNs

Salesforce Research(Salesforce 研究院)

Stephen Merity, Bryan McCann, Richard Socher

摘要:

递归神经网络(RNN)是自然语言处理中许多序列任务的基本构建块。最近的研究集中在经常性的辍学技术或自定义RNN细胞,以提高性能。这两种方法都需要对机器学习模型或底层RNN配置进行大量修改。我们重新审视了传统的正则化技术,特别是RNN激活的L2正则化和连续隐藏状态的慢度正则化,以提高RNN在语言建模任务中的性能。这两种技术都需要对现有的RNN架构进行最小的修改,并导致与更复杂的正则化技术或自定义单元架构相当或更好的性能改进。这些正则化技术可以在优化的LSTM实现(如NVIDIA cuDNN LSTM)上使用,而无需任何修改。

英文摘要:

Recurrent neural networks (RNNs) serve as a fundamental building block for many sequence tasks across natural language processing. Recent research has focused on recurrent dropout techniques or custom RNN cells in order to improve performance. Both of these can require substantial modifications to the machine learning model or to the underlying RNN configurations. We revisit traditional regularization techniques, specifically L2 regularization on RNN activations and slowness regularization over successive hidden states, to improve the performance of RNNs on the task of language modeling. Both of these techniques require minimal modification to existing RNN architectures and result in performance improvements comparable or superior to more complicated regularization techniques or custom cell architectures. These regularization techniques can be used without any modification on optimized LSTM implementations such as the NVIDIA cuDNN LSTM.

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。

↑