Improving Neural Language Models with a Continuous CacheDownload PDF

04 Dec 2020 (modified: 01 Mar 2017)ICLR 2017 conference submissionReaders: Everyone
  • Abstract: We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which stores past hidden activations as memory and accesses them through a dot product with the current hidden activation. This mechanism is very efficient and scales to very large memory sizes. We also draw a link between the use of external memory in neural network and cache models used with count based language models. We demonstrate on several language model datasets that our approach performs significantly better than recent memory augmented networks.
  • Keywords: Natural language processing
  • Conflicts: fb.com, columbia.edu
14 Replies

Loading