Proceedings

A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework

Siting Liang, Omar Adjali, Omair Shahzad Bhatti, Daniel Sonntag

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8449-8452.

https://doi.org/10.24963/ijcai.2026/977

Keywords

  • AI: Humans and AI
  • AI: Machine Learning
  • AI: Natural Language Processing

Abstract

Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on dataset-specific designs, limiting scalability and cross-domain generalization. We propose a unified generative, sequence-to-sequence framework that performs all event extraction subtasks jointly and supports both end-to-end and pipeline configurations. We fine-tune pre-trained language models on multiple event datasets across diverse domains, enabling a single model to retain domain-specific semantics while generalizing over large, evolving label spaces. Cross-domain experiments show strong, robust performance across datasets, demonstrating a scalable solution for real-world event extraction. We demonstrate these capabilities through a web-based application tailored for researchers and practitioners. The platform supports inspection of different configurations and facilitates cross-domain comparisons.

Siting Liang, Omar Adjali, Omair Shahzad Bhatti, and Daniel Sonntag. 2026. A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8449–8452. https://doi.org/10.24963/ijcai.2026/977
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards