Event Causality Is Key to Computational Story Understanding

arXiv:2311.09648v2 Announce Type: replace
Abstract: Cognitive science and symbolic AI research suggest that event causality provides vital information for story understanding. However, machine learning systems for story understanding rarely employ event causality, partially due to the lack of methods that reliably identify open-world causal event relations. Leveraging recent progress in large language models, we present the first method for event causality identification that leads to material improvements in computational story understanding. Our technique sets a new state of the art …

arxiv causality computational cs.cl event key story type understanding