TY - JOUR AU - Pichotta, Karl AU - Mooney, Raymond PY - 2016/03/05 Y2 - 2024/03/28 TI - Learning Statistical Scripts with LSTM Recurrent Neural Networks JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 30 IS - 1 SE - Technical Papers: NLP and Machine Learning DO - 10.1609/aaai.v30i1.10347 UR - https://ojs.aaai.org/index.php/AAAI/article/view/10347 SP - AB - <p> 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. </p> ER -