Open Domain Event Extraction Using Neural Latent Variable Models

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.

accepted by ACL 2019

References in corpus (4)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
• Autoencoding Variational Inference For Topic Models
• Probabilistic Frame Induction

Cited by in corpus (7)

• Forecasting Crude Oil Price Using Event Extraction
• Dialogue State Induction Using Neural Latent Variable Models
• MAVEN: A Massive General Domain Event Detection Dataset
• An overview of event extraction and its applications
• GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction
• ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
• Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding