A Probabilistic-Logic based Commonsense Representation Framework for Modelling Inferences with Multiple Antecedents and Varying Likelihoods

TL;DR

This paper introduces a probabilistic-logic based framework for commonsense knowledge graphs that captures nuanced, multi-conditional inferences with varying likelihoods, organized hierarchically for improved reasoning and interpretability.

Contribution

It proposes a novel probabilistic-logic and hierarchical ontology framework to enhance commonsense knowledge representation beyond existing declarative graphs.

Findings

Extended PrimeNet with the new framework via crowd-sourcing and expert annotation.

Improved interpretability in passage-based semantic parsing and question answering.

Enables encoding of diverse world knowledge with flexible, grounded, and free-text beliefs.

Abstract

Commonsense knowledge-graphs (CKGs) are important resources towards building machines that can 'reason' on text or environmental inputs and make inferences beyond perception. While current CKGs encode world knowledge for a large number of concepts and have been effectively utilized for incorporating commonsense in neural models, they primarily encode declarative or single-condition inferential knowledge and assume all conceptual beliefs to have the same likelihood. Further, these CKGs utilize a limited set of relations shared across concepts and lack a coherent knowledge organization structure resulting in redundancies as well as sparsity across the larger knowledge graph. Consequently, today's CKGs, while useful for a first level of reasoning, do not adequately capture deeper human-level commonsense inferences which can be more nuanced and influenced by multiple contextual or situational factors. Accordingly, in this work, we study how commonsense knowledge can be better represented by -- (i) utilizing a probabilistic logic representation scheme to model composite inferential knowledge and represent conceptual beliefs with varying likelihoods and (ii) incorporating a hierarchical conceptual ontology to identify salient concept-relevant relations and organize beliefs at different conceptual levels. Our resulting knowledge representation framework can encode a wider variety of world knowledge and represent beliefs flexibly using grounded concepts as well as free-text phrases. As a result, the framework can be utilized as both a traditional free-text knowledge graph and a grounded logic-based inference system more suitable for neuro-symbolic applications. We describe how we extend the PrimeNet knowledge base with our framework through crowd-sourcing and expert-annotation, and demonstrate its application for more interpretable passage-based semantic parsing and question answering.