Year: 2016
Type: preprint
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.
Source: arXiv (Cornell University)
Institutions: Columbia University, Meta (Israel)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2571859396