Reference-Aware Language Models

Zichao Yang, Phil Blunsom, Chris Dyer, Wang Ling

Nov 04, 2016 (modified: Jan 17, 2017) ICLR 2017 conference submission readers: everyone
  • Abstract: We propose a general class of language models that treat reference as an explicit stochastic latent variable. This architecture allows models to create mentions of entities and their attributes by accessing external databases (required by, e.g., dialogue generation and recipe generation) and internal state (required by, e.g. language models which are aware of coreference). This facilitates the incorporation of information that can be accessed in predictable locations in databases or dis- course context, even when the targets of the reference may be rare words. Experiments on three tasks show our model variants outperform models based on deterministic attention.
  • TL;DR: reference-aware language models
  • Conflicts:,
  • Keywords: Natural language processing, Deep learning