Learning Statistical Scripts with LSTM Recurrent Neural Networks (2016)
Karl Pichotta and Raymond J. Mooney
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.
In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, Arizona, February 2016.

Slides (PDF) Slides (PPT)
Raymond J. Mooney Faculty mooney [at] cs utexas edu