CSKG: The CommonSense Knowledge Graph

TL;DR

This paper introduces CSKG, an integrated commonsense knowledge graph combining seven sources, and demonstrates its utility for reasoning and language model pre-training, supporting further research in the field.

Contribution

The paper presents the first integrated commonsense knowledge graph, CSKG, combining multiple sources and analyzing its structure and embeddings for improved reasoning and language model pre-training.

Findings

CSKG is well-connected and facilitates reasoning.

Embeddings of CSKG improve downstream tasks.

CSKG and embeddings are publicly available for research.

Abstract

Sources of commonsense knowledge support applications in natural language understanding, computer vision, and knowledge graphs. Given their complementarity, their integration is desired. Yet, their different foci, modeling approaches, and sparse overlap make integration difficult. In this paper, we consolidate commonsense knowledge by following five principles, which we apply to combine seven key sources into a first integrated CommonSense Knowledge Graph (CSKG). We analyze CSKG and its various text and graph embeddings, showing that CSKG is well-connected and that its embeddings provide a useful entry point to the graph. We demonstrate how CSKG can provide evidence for generalizable downstream reasoning and for pre-training of language models. CSKG and all its embeddings are made publicly available to support further research on commonsense knowledge integration and reasoning.