elBERto: Self-supervised commonsense learning for question answering

作者：

Highlights：

• A self-supervised learning method is proposed to solve commonsense QA task.

• A novel CRL task and a JP task are presented to facilitate commonsense learning.

• Experiments verify that elBERTo significantly outperforms the existing algorithms.

摘要

•A self-supervised learning method is proposed to solve commonsense QA task.•A novel CRL task and a JP task are presented to facilitate commonsense learning.•Experiments verify that elBERTo significantly outperforms the existing algorithms.

论文关键词：Question answering,Self-supervised learning,Commonsense reasoning

论文评审过程：Received 4 March 2022, Revised 24 September 2022, Accepted 28 September 2022, Available online 7 October 2022, Version of Record 21 October 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109964