Revisiting Activation Regularization for Language RNNs

Abstract

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.

References in corpus (7)

• Neural Architecture Search with Reinforcement Learning
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Recurrent Neural Network Regularization
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
• Pointer Sentinel Mixture Models
• Quasi-Recurrent Neural Networks
• Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling

Cited by in corpus (2)

• Regularizing and Optimizing LSTM Language Models
• Variational Bi-LSTMs