Learning Statistical Scripts with LSTM Recurrent Neural Networks

AAAI 2016 pp. 2800-2806

doi:10.1609/AAAI.V30I1.10347 /aaai/2016/pichotta2016aaai-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.

PDF AAAI Semantic Scholar

Cite

Text

Pichotta and Mooney. "Learning Statistical Scripts with LSTM Recurrent Neural Networks." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10347

Markdown

[Pichotta and Mooney. "Learning Statistical Scripts with LSTM Recurrent Neural Networks." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/pichotta2016aaai-learning/) doi:10.1609/AAAI.V30I1.10347

BibTeX

@inproceedings{pichotta2016aaai-learning,
  title     = {{Learning Statistical Scripts with LSTM Recurrent Neural Networks}},
  author    = {Pichotta, Karl and Mooney, Raymond J.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {2800-2806},
  doi       = {10.1609/AAAI.V30I1.10347},
  url       = {https://mlanthology.org/aaai/2016/pichotta2016aaai-learning/}
}