Inference of Fine-Grained Event Causality from Blogs and Films

TL;DR

This paper presents an unsupervised method to learn fine-grained causal relations between events from narratives like blogs and films, showing high accuracy and novel event pairs not found in news datasets.

Contribution

It introduces a new approach focusing on narrative genres for causal relation learning, demonstrating effective extraction of causal event pairs from unstructured text.

Findings

Over 80% human-judged causal likelihood

Learned event pairs are novel compared to news datasets

Method effective in narrative genres

Abstract

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.