COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective

TL;DR

This paper introduces COLA, a zero-shot framework for detecting commonsense causal relations between events within their context, leveraging causal inference techniques to improve accuracy over existing methods.

Contribution

It proposes a novel task of contextualized causality detection and develops COLA, a framework that incorporates causal inference principles for improved zero-shot performance.

Findings

COLA outperforms baseline models in causality detection accuracy.

The framework effectively utilizes temporality and covariate balancing.

Experimental results demonstrate the importance of context in causal reasoning.

Abstract

Detecting commonsense causal relations (causation) between events has long been an essential yet challenging task. Given that events are complicated, an event may have different causes under various contexts. Thus, exploiting context plays an essential role in detecting causal relations. Meanwhile, previous works about commonsense causation only consider two events and ignore their context, simplifying the task formulation. This paper proposes a new task to detect commonsense causation between two events in an event sequence (i.e., context), called contextualized commonsense causal reasoning. We also design a zero-shot framework: COLA (Contextualized Commonsense Causality Reasoner) to solve the task from the causal inference perspective. This framework obtains rich incidental supervision from temporality and balances covariates from multiple timestamps to remove confounding effects. Our extensive experiments show that COLA can detect commonsense causality more accurately than baselines.