Inference of Fine-Grained Event Causality from Blogs and Films
This work addresses the problem of acquiring causal knowledge for narrative understanding, which is incremental as it focuses on alternative data sources rather than a new paradigm.
The paper argues that newswire is a poor source for learning fine-grained causal relations between everyday events and demonstrates an unsupervised method that learns such relations from blogs and films, achieving over 80% human-judged causality accuracy.
Human understanding of narrative is mainly driven by reasoning about causal relations between events and thus recognizing them is a key capability for computational models of language understanding. Computational work in this area has approached this via two different routes: by focusing on acquiring a knowledge base of common causal relations between events, or by attempting to understand a particular story or macro-event, along with its storyline. In this position paper, we focus on knowledge acquisition approach and claim that newswire is a relatively poor source for learning fine-grained causal relations between everyday events. We describe experiments using an unsupervised method to learn causal relations between events in the narrative genres of first-person narratives and film scene descriptions. We show that our method learns fine-grained causal relations, judged by humans as likely to be causal over 80% of the time. We also demonstrate that the learned event pairs do not exist in publicly available event-pair datasets extracted from newswire.