Knowledge graph embedding is aimed at representing entities and relations of knowledge graph in a low-dimensional continuous vector space. Previous embedding models pay little attention to the sequential semantic information in triples and as a result, may lead to the semantic drift problem. Towards this end, we propose a novel sequential semantic embedding (SeqSemE) model to address this problem in this paper. Firstly, we utilize a sequential language model to capture sequential information of triples and interactions between entities and relations. Secondly, we propose a method of learning two embeddings for each relation to avoid semantic drift. Extensive experiments on link prediction show that our SeqSemE is efficient and effective. It can obtain better performance than previous state-of-the-art embedding models.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Sequential Semantic Knowledge Graph Embedding


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Wu, Meiping (editor) / Niu, Yifeng (editor) / Gu, Mancang (editor) / Cheng, Jin (editor) / Shang, Yu-Ming (author) / Huang, Heyan (author) / Yuan, Yan (author)

    Conference:

    International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021



    Publication date :

    2022-03-18


    Size :

    11 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Graph attribute embedding via Riemannian submersion learning

    Zhao, H. / Robles-Kelly, A. / Zhou, J. et al. | British Library Online Contents | 2011


    A generative model for graph matching and embedding

    Xiao, B. / Hancock, E. R. / Wilson, R. C. | British Library Online Contents | 2009


    Real-time mosaic using sequential graph

    Kim, D.-W. / Hong, K.-S. | British Library Online Contents | 2006