Visually Grounded Commonsense Knowledge Acquisition

Yuan Yao , Tianyu Yu , Ao Zhang , Mengdi Li , Ruobing Xie , Cornelius Weber , Zhiyuan Liu , Haitao Zheng , Stefan Wermter , Tat-Seng Chua , Maosong Sun
Proceedings of the AAAI Conference on Artificial Intelligence Volume 37, Number 5, pages 6583-6592, doi: 10.1609/aaai.v37i5.25809 - Jun 2023
Associated documents :  
Large-scale commonsense knowledge bases empower a broad range of AI applications, where the automatic extraction of commonsense knowledge (CKE) is a fundamental and challenging problem. CKE from text is known for suffering from the inherent sparsity and reporting bias of commonsense in text. Visual perception, on the other hand, contains rich commonsense knowledge about real-world entities, e.g., (person, can_hold, bottle), which can serve as promising sources for acquiring grounded commonsense knowledge. In this work, we present CLEVER, which formulates CKE as a distantly supervised multi-instance learning problem, where models learn to summarize commonsense relations from a bag of images about an entity pair without any human annotation on image instances. To address the problem, CLEVER leverages vision-language pre-training models for deep understanding of each image in the bag, and selects informative instances from the bag to summarize commonsense entity relations via a novel contrastive attention mechanism. Comprehensive experimental results in held-out and human evaluation show that CLEVER can extract commonsense knowledge in promising quality, outperforming pre-trained language model-based methods by 3.9 AUC and 6.4 mAUC points. The predicted commonsense scores show strong correlation with human judgment with a 0.78 Spearman coefficient. Moreover, the extracted commonsense can also be grounded into images with reasonable interpretability. The data and codes can be obtained at


 	 author =  {Yao, Yuan and Yu, Tianyu and Zhang, Ao and Li, Mengdi and Xie, Ruobing and Weber, Cornelius and Liu, Zhiyuan and Zheng, Haitao and Wermter, Stefan and Chua, Tat-Seng and Sun, Maosong},  
 	 title = {Visually Grounded Commonsense Knowledge Acquisition}, 
 	 booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
 	 journal = {},
 	 number = {5},
 	 volume = {37},
 	 pages = {6583-6592},
 	 year = {2023},
 	 month = {Jun},
 	 publisher = {},
 	 doi = {10.1609/aaai.v37i5.25809},