Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory. To enable this, machines need to have a more general understanding of our complicated world and develop the ability to perform common-sense reasoning besides fitting the specific downstream tasks. External commonsense knowledge graphs (KGs), such as ConceptNet, provide rich information about words and their relationships. Thus, towards general common-sense learning, we propose two approaches to implicitly and explicitly infuse such KGs into pretrained language models. We demonstrate our proposed methods perform well on So-ciallQA, a social commonsense reasoning task, in both limited and full training data regimes.
展开▼
