English

Open Domain Event Extraction Using Neural Latent Variable Models

Computation and Language 2022-12-19 v1

Abstract

We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters. A novel latent variable neural model is constructed, which is scalable to very large corpus. A dataset is collected and manually annotated, with task-specific evaluation metrics being designed. Results show that the proposed unsupervised model gives better performance compared to the state-of-the-art method for event schema induction.

Keywords

Cite

@article{arxiv.1906.06947,
  title  = {Open Domain Event Extraction Using Neural Latent Variable Models},
  author = {Xiao Liu and Heyan Huang and Yue Zhang},
  journal= {arXiv preprint arXiv:1906.06947},
  year   = {2022}
}

Comments

accepted by ACL 2019

R2 v1 2026-06-23T09:55:26.572Z