State gradients for analyzing memory in LSTM language models

This publication has 6 references indexed in Scilit:

• Representation of Linguistic Form and Function in Recurrent Neural Networks
  Computational Linguistics, 2017
• LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
  IEEE Transactions on Visualization and Computer Graphics, 2017
• Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
  Transactions of the Association for Computational Linguistics, 2016
• LSTM recurrent networks learn simple context-free and context-sensitive languages
  IEEE Transactions on Neural Networks, 2001
• Long Short-Term Memory
  Neural Computation, 1997
• Finding Structure in Time
  Cognitive Science, 1990