Semantic Categorization of Social Knowledge for Commonsense Question Answering
This work addresses the need for interpretable commonsense knowledge in QA systems, though it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of understanding what specific commonsense knowledge is needed for question answering by semantically categorizing social knowledge in the SocialIQA dataset, and their models incorporating these categories achieved comparable performance with simpler, smaller architectures than complex alternatives.
Large pre-trained language models (PLMs) have led to great success on various commonsense question answering (QA) tasks in an end-to-end fashion. However, little attention has been paid to what commonsense knowledge is needed to deeply characterize these QA tasks. In this work, we proposed to categorize the semantics needed for these tasks using the SocialIQA as an example. Building upon our labeled social knowledge categories dataset on top of SocialIQA, we further train neural QA models to incorporate such social knowledge categories and relation information from a knowledge base. Unlike previous work, we observe our models with semantic categorizations of social knowledge can achieve comparable performance with a relatively simple model and smaller size compared to other complex approaches.