CSKG: The CommonSense Knowledge Graph

被引:41
|
作者
Ilievski, Filip [1 ]
Szekely, Pedro [1 ]
Zhang, Bin [1 ]
机构
[1] Univ Southern Calif, Informat Sci Inst, Los Angeles, CA 90007 USA
来源
SEMANTIC WEB, ESWC 2021 | 2021年 / 12731卷
关键词
Commonsense knowledge; Knowledge graph; Embeddings;
D O I
10.1007/978-3-030-77385-4_41
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sources of commonsense knowledge support applications in natural language understanding, computer vision, and knowledge graphs. Given their complementarity, their integration is desired. Yet, their different foci, modeling approaches, and sparse overlap make integration difficult. In this paper, we consolidate commonsense knowledge by following five principles, which we apply to combine seven key sources into a first integrated CommonSense Knowledge Graph (CSKG). We analyze CSKG and its various text and graph embeddings, showing that CSKG is well-connected and that its embeddings provide a useful entry point to the graph. We demonstrate how CSKG can provide evidence for generalizable downstream reasoning and for pre-training of language models. CSKG and all its embeddings are made publicly available to support further research on commonsense knowledge integration and reasoning.
引用
收藏
页码:680 / 696
页数:17
相关论文
共 50 条
  • [1] Inductive Learning on Commonsense Knowledge Graph Completion
    Wang, Bin
    Wang, Guangtao
    Huang, Jing
    You, Jiaxuan
    Leskovec, Jure
    Kuo, C-C Jay
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [2] Graph neural topic model with commonsense knowledge
    Zhu, Bingshan
    Cai, Yi
    Ren, Haopeng
    INFORMATION PROCESSING & MANAGEMENT, 2023, 60 (02)
  • [3] IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions
    Zeng, Ziheng
    Cheng, Kellen Tan
    Nanniyur, Srihari Venkat
    Zuo, Jianing
    Bhat, Suma
    2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2023), 2023, : 14243 - 14264
  • [4] ImageSchemaNet: A framester graph for embodied commonsense knowledge
    De Giorgis, Stefano
    Gangemi, Aldo
    Gromann, Dagmar
    SEMANTIC WEB, 2024, 15 (04) : 1417 - 1441
  • [5] Fusing Context Into Knowledge Graph for Commonsense Question Answering
    Xu, Yichong
    Zhu, Chenguang
    Xu, Ruochen
    Liu, Yang
    Zeng, Michael
    Huang, Xuedong
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 1201 - 1207
  • [6] CKGAC: A Commonsense Knowledge Graph About Attributes of Concepts
    Wang, Ya
    Cao, Cungen
    Chen, Zhiwen
    Wang, Shi
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, 2022, 13368 : 585 - 601
  • [7] ECCKG: An Eventuality-Centric Commonsense Knowledge Graph
    Wang, Ya
    Cao, Cungen
    Chen, Zhiwen
    Wang, Shi
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, 2022, 13368 : 568 - 584
  • [8] Commonsense Knowledge Aware Conversation Generation with Graph Attention
    Zhou, Hao
    Young, Tom
    Huang, Minlie
    Zhao, Haizhou
    Xu, Jingfang
    Zhu, Xiaoyan
    PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 4623 - 4629
  • [9] Knowledge Graph Compression Enhances Diverse Commonsense Generation
    Hwang, EunJeong
    Thost, Veronika
    Shwartz, Vered
    Ma, Tengfei
    2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2023, 2023, : 558 - 572
  • [10] CSKG4APT: A Cybersecurity Knowledge Graph for Advanced Persistent Threat Organization Attribution
    Ren, Yitong
    Xiao, Yanjun
    Zhou, Yinghai
    Zhang, Zhiyong
    Tian, Zhihong
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (06) : 5695 - 5709