ROCK: Causal Inference Principles for Reasoning about Commonsense Causality
This work addresses the problem of improving commonsense reasoning in AI for natural language processing, offering a foundational approach to reduce reliance on deep language models and mitigate confounding biases.
The paper tackles the lack of a theoretical framework for commonsense causality reasoning (CCR) by proposing ROCK, a novel framework that adapts causal inference principles to balance confounding effects using temporal signals, achieving good capabilities in zero-shot settings.
Commonsense causality reasoning (CCR) aims at identifying plausible causes and effects in natural language descriptions that are deemed reasonable by an average person. Although being of great academic and practical interest, this problem is still shadowed by the lack of a well-posed theoretical framework; existing work usually relies on deep language models wholeheartedly, and is potentially susceptible to confounding co-occurrences. Motivated by classical causal principles, we articulate the central question of CCR and draw parallels between human subjects in observational studies and natural languages to adopt CCR to the potential-outcomes framework, which is the first such attempt for commonsense tasks. We propose a novel framework, ROCK, to Reason O(A)bout Commonsense K(C)ausality, which utilizes temporal signals as incidental supervision, and balances confounding effects using temporal propensities that are analogous to propensity scores. The ROCK implementation is modular and zero-shot, and demonstrates good CCR capabilities.