CHRONOS: A Schema-Based Event Understanding and Prediction System

Abstract

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.

Cite

Text

Chang et al. "CHRONOS: A Schema-Based Event Understanding and Prediction System." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30323

Markdown

[Chang et al. "CHRONOS: A Schema-Based Event Understanding and Prediction System." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/chang2024aaai-chronos/) doi:10.1609/AAAI.V38I21.30323

BibTeX

@inproceedings{chang2024aaai-chronos,
  title     = {{CHRONOS: A Schema-Based Event Understanding and Prediction System}},
  author    = {Chang, Maria and Fokoue, Achille and Uceda-Sosa, Rosario and Awasthy, Parul and Barker, Ken and Kumaravel, Sadhana and Hassanzadeh, Oktie and Soares, Elton F. S. and Gao, Tian and Bhattacharjya, Debarun and Florian, Radu and Roukos, Salim},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {22871-22877},
  doi       = {10.1609/AAAI.V38I21.30323},
  url       = {https://mlanthology.org/aaai/2024/chang2024aaai-chronos/}
}