Think Again Networks, the Delta Loss, and an Application in Language Modeling

• Abstract
• Abstract (translated by Google)
• URL
• PDF

Abstract

This short paper introduces an abstraction called Think Again Networks (ThinkNet) which can be applied to any state-dependent function (such as a recurrent neural network). Here we show a simple application in Language Modeling which achieves state of the art perplexity on the Penn Treebank.

Abstract (translated by Google)

URL

http://arxiv.org/abs/1904.11816

PDF

http://arxiv.org/pdf/1904.11816