Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering

TL;DR

This paper introduces a neuro-symbolic method for zero-shot commonsense question answering that dynamically constructs knowledge graphs on demand, improving reasoning and interpretability over static knowledge bases.

Contribution

It proposes a novel approach that generates contextually relevant symbolic knowledge structures using generative models, enabling reasoning in zero-shot scenarios.

Findings

Significant performance improvements over pretrained language models.

Effective dynamic knowledge graph construction for reasoning.

Provides interpretable reasoning paths for predictions.

Abstract

Understanding narratives requires reasoning about implicit world knowledge related to the causes, effects, and states of situations described in text. At the core of this challenge is how to access contextually relevant knowledge on demand and reason over it. In this paper, we present initial studies toward zero-shot commonsense question answering by formulating the task as inference over dynamically generated commonsense knowledge graphs. In contrast to previous studies for knowledge integration that rely on retrieval of existing knowledge from static knowledge graphs, our study requires commonsense knowledge integration where contextually relevant knowledge is often not present in existing knowledge bases. Therefore, we present a novel approach that generates contextually-relevant symbolic knowledge structures on demand using generative neural commonsense knowledge models. Empirical results on two datasets demonstrate the efficacy of our neuro-symbolic approach for dynamically constructing knowledge graphs for reasoning. Our approach achieves significant performance boosts over pretrained language models and vanilla knowledge models, all while providing interpretable reasoning paths for its predictions.