Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

Understand

In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge.

• However, how to engage commonsense effectively in question answering systems is still under exploration in both research academia and industry.
• In this paper, we propose a novel question-answering method by integrating multiple knowledge sources, i.e.
• ConceptNet, Wikipedia, and the Cambridge Dictionary, to boost the performance.