Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks

Lisa Bauer, Mohit Bansal
2021 Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   unpublished
Integrating external knowledge into commonsense reasoning tasks has shown progress in resolving some, but not all, knowledge gaps in these tasks. For knowledge integration to yield peak performance, it is critical to select a knowledge graph (KG) that is well-aligned with the given task's objective. We present an approach to assess how well a candidate KG can correctly identify and accurately fill in gaps of reasoning for a task, which we call KG-to-task match. We show this KGto-task match in 3
more » ... phases: knowledge-task identification, knowledge-task alignment, and knowledge-task integration. We also analyze our transformer-based KG-to-task models via commonsense probes to measure how much knowledge is captured in these models before and after KG integration.
doi:10.18653/v1/2021.eacl-main.192 fatcat:srlgycbh3rajlkgvf2fr5jicqq