← 返回论文检索
AAAI 2024official proceedings

CHRONOS: A Schema-Based Event Understanding and Prediction System

Maria Chang, Achille Fokoue, Rosario Uceda-Sosa, Parul Awasthy, Ken Barker, Sadhana Kumaravel, Oktie Hassanzadeh, Elton Soares, Tian Gao, Debarun Bhattacharjya, Radu Florian, Salim Roukos

PDF 由论文原始站点提供,PaperCompass 不保存论文文件。DOI 10.1609/aaai.v38i21.30323 ↗

摘要

Chronological and Hierarchical Reasoning Over Naturally Occurring Schemas (CHRONOS) is a system that combines language model-based natural language processing with symbolic knowledge representations to analyze and make predictions about newsworthy events. CHRONOS consists of an event-centric information extraction pipeline and a complex event schema instantiation and prediction system. Resulting predictions are detailed with arguments, event types from Wikidata, schema-based justifications, and source document provenance. We evaluate our system by its ability to capture the structure of unseen events described in news articles and make plausible predictions as judged by human annotators.