no code implementations • EMNLP 2021 • Weinan He, Canming Huang, Yongmei Liu, Xiaodan Zhu
To better evaluate NLMs, we propose a logic-based framework that focuses on high-quality commonsense knowledge.
no code implementations • Findings (EMNLP) 2021 • Canming Huang, Weinan He, Yongmei Liu
Recent methods based on pre-trained language models have shown strong supervised performance on commonsense reasoning.
no code implementations • CVPR 2023 • Yixin Zhang, Zilei Wang, Weinan He
To this end, we first regard the classifier weights of the source model as class prototypes to compute class relationship, and then propose a novel probability-based similarity between target-domain samples by embedding the source-domain class relationship, resulting in Class Relationship embedded Similarity (CRS).
no code implementations • 25 Nov 2022 • Weinan He, Canming Huang, Zhanhao Xiao, Yongmei Liu
Reasoning about actions and change (RAC) is essential to understand and interact with the ever-changing environment.