Pointer Sentinel Mixture Models
Stephen Merity, Caiming Xiong, James Bradbury et al. · arXiv (Cornell University) · 2016
Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies. Even then they struggle to predict rare or unseen words even if the context makes the prediction unambiguous. We introduce the pointer sentinel mixture architecture for neural sequence models which has the ability to either reproduce a word from the recent context or produce a word from a standard softmax classifier. Our pointer sentinel-LSTM model achieves state of the art language modeling performance on the Penn Treebank (70.9 perplexity) while using far fewer parameters than a standard softmax LSTM. In order to evaluate how well language models can exploit longer contexts and deal with more realistic vocabularies and larger corpora we also introduce the freely available WikiText corpus.
Cited by 427 works. doi:10.48550/arxiv.1609.07843 Open-access PDF
Authors
References
- Moses
- Recurrent Neural Network Regularization
- A maximum entropy approach to adaptive statistical language modelling
- Pointer networks
- Context dependent recurrent neural network language model
- A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
- Dynamic Memory Networks for Visual and Textual Question Answering
- Text Understanding with the Attention Sum Reader Network
- How to Construct Deep Recurrent Neural Networks
- Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations