Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation

A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it remains unclear: (1) How far can we get by exploiting external for CQA? (2) much potential has exploited current CQA models? (3) Which are the most promising directions future To answer these questions, benchmark conducting extensive experiments on multiple standard datasets using a simple effective knowledge-to-text transformation framework. Experiments show that: Our framework achieves state-of-the-art performance CommonsenseQA dataset, providing strong baseline CQA; The still from being fully — there significant gap models our with golden knowledge; Context-sensitive selection, heterogeneous exploitation, commonsense-rich directions.