Event Process Typing via Hierarchical Optimal Transport

Authors

  • Bo Zhou School of Artificial Intelligence, University of Chinese Academy of Sciences National Laboratory of Pattern Recognition, CASIA
  • Yubo Chen School of Artificial Intelligence, University of Chinese Academy of Sciences National Laboratory of Pattern Recognition, CASIA
  • Kang Liu School of Artificial Intelligence, University of Chinese Academy of Sciences National Laboratory of Pattern Recognition, CASIA Beijing Academy of Artificial Intelligence
  • Jun Zhao School of Artificial Intelligence, University of Chinese Academy of Sciences National Laboratory of Pattern Recognition, CASIA

DOI:

https://doi.org/10.1609/aaai.v37i11.26643

Keywords:

SNLP: Sentence-Level Semantics and Textual Inference

Abstract

Understanding intention behind event processes in texts is important to many applications. One challenging task in this line is event process typing, which aims to tag the process with one action label and one object label describing the overall action of the process and object the process likely affects respectively. To tackle this task, existing methods mainly rely on the matching of the event process level and label level representation, which ignores two important characteristics: Process Hierarchy and Label Hierarchy. In this paper, we propose a Hierarchical Optimal Transport (HOT) method to address the above problem. Specifically, we first explicitly extract the process hierarchy and label hierarchy. Then the HOT optimally matches the two types of hierarchy. Experimental results show that our model outperforms the baseline models, illustrating the effectiveness of our model.

Downloads

Published

2023-06-26

How to Cite

Zhou, B., Chen, Y., Liu, K., & Zhao, J. (2023). Event Process Typing via Hierarchical Optimal Transport. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 14038-14046. https://doi.org/10.1609/aaai.v37i11.26643

Issue

Section

AAAI Technical Track on Speech & Natural Language Processing