What Happens Next? Future Subevent Prediction Using Contextual Hierarchical LSTM


  • Linmei Hu Tsinghua University
  • Juanzi Li Tsinghua University
  • Liqiang Nie Shandong University
  • Xiao-Li Li A*STAR
  • Chao Shao Tsinghua University




event prediction, LSTM, subevent sequence


Events are typically composed of a sequence of subevents. Predicting a future subevent of an event is of great importance for many real-world applications. Most previous work on event prediction relied on hand-crafted features and can only predict events that already exist in the training data. In this paper, we develop an end-to-end model which directly takes the texts describing previous subevents as input and automatically generates a short text describing a possible future subevent. Our model captures the two-level sequential structure of a subevent sequence, namely, the word sequence for each subevent and the temporal order of subevents. In addition, our model incorporates the topics of the past subevents to make context-aware prediction of future subevents. Extensive experiments on a real-world dataset demonstrate the superiority of our model over several state-of-the-art methods.




How to Cite

Hu, L., Li, J., Nie, L., Li, X.-L., & Shao, C. (2017). What Happens Next? Future Subevent Prediction Using Contextual Hierarchical LSTM. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.11001