文献类型：期刊文献

英文题名：A multi-view representation learning framework for commonsense knowledge bases

作者：Zhang, Weiyan[1];Chen, Chuang[1];Chen, Tao[2];Liu, Jingping[1];Ye, Qi[1];Ruan, Tong[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China;[2]Fudan Univ, Sch Comp Sci, Shanghai Key Lab Data Sci, Shanghai, Peoples R China

年份：2024

卷号：674

外文期刊名：INFORMATION SCIENCES

收录：;EI(收录号：20242016093984);WOS:【SCI-EXPANDED(收录号:WOS:001242605800001)】；

基金：This paper is supported by the fund of the National Natural Science Foundation of China (No. 62306112) , the Shanghai Sailing Program (No. 23YF1409400) , the National Key Research and Development Program of China (2021YFC2701800, 2021YFC2701801) , and Shanghai Pilot Program for Basic Research (No. 22TQ1400100-20) .

语种：英文

外文关键词：Commonsense knowledge; Representation learning; Multi-view learning

摘要：Commonsense knowledge bases play an essential role in a wide range of natural language processing tasks. This paper studies the problem of representation learning for commonsense knowledge bases to effectively incorporate their knowledge into numerical models. Most existing knowledge base representation learning methods are difficult to apply to commonsense knowledge bases since they are much sparser than general knowledge bases. Hence, in this paper, we propose a novel method for commonsense knowledge base representation learning. Specifically, we first model the nodes from multiple views, including word/phase information, context information, and graph information. Then, we design a scoring function to measure whether the commonsense triplets are established through relation representation learning. We conduct extensive experiments on two tasks and the results show that our proposed model outperforms other knowledge base representation learning methods.