Pointer Sentinel Mixture Models

Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher

Nov 03, 2016 (modified: Mar 03, 2017) ICLR 2017 conference submission readers: everyone
  • Abstract: 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 corpora we also introduce the freely available WikiText corpus.
  • TL;DR: Pointer sentinel mixture models provide a method to combine a traditional vocabulary softmax with a pointer network, providing state of the art results in language modeling on PTB and the newly introduced WikiText with few extra parameters.
  • Conflicts: salesforce.com
  • Keywords: Natural language processing, Deep learning