Learning Statistical Scripts with LSTM Recurrent Neural Networks

Authors

  • Karl Pichotta The University of Texas at Austin
  • Raymond Mooney The University of Texas at Austin

Keywords:

Natural Language Processing, Deep Learning

Abstract

Scripts encode knowledge of prototypical sequences of events. We describe a Recurrent Neural Network model for statistical script learning using Long Short-Term Memory, an architecture which has been demonstrated to work well on a range of Artificial Intelligence tasks. We evaluate our system on two tasks, inferring held-out events from text and inferring novel events from text, substantially outperforming prior approaches on both tasks.

Downloads

Published

2016-03-05

How to Cite

Pichotta, K., & Mooney, R. (2016). Learning Statistical Scripts with LSTM Recurrent Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/10347

Issue

Section

Technical Papers: NLP and Machine Learning