Relation and Fact Type Supervised Knowledge Graph Embedding via Weighted Scores

被引:2
作者
Zhou, Bo [1 ,2 ]
Chen, Yubo [1 ]
Liu, Kang [1 ,2 ]
Zhao, Jun [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
来源
CHINESE COMPUTATIONAL LINGUISTICS, CCL 2019 | 2019年 / 11856卷
基金
中国国家自然科学基金;
关键词
Knowledge graph embedding; Relation supervised; Fact type supervised; Weighted scores;
D O I
10.1007/978-3-030-32381-3_21
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Knowledge graph embedding aims at learning low-dimensional representations for entities and relations in knowledge graph. Previous knowledge graph embedding methods use just one score to measure the plausibility of a fact, which can't fully utilize the latent semantics of entities and relations. Meanwhile, they ignore the type of relations in knowledge graph and don't use fact type explicitly. We instead propose a model to fuse different scores of a fact and utilize relation and fact type information to supervise the training process. Specifically, scores by inner product of a fact and scores by neural network are fused with different weights to measure the plausibility of a fact. For each fact, besides modeling the plausibility, the model learns to classify different relations and differentiate positive facts from negative ones which can be seen as a muti-task method. Experiments show that our model achieves better link prediction performance than multiple strong baselines on two benchmark datasets WN18 and FB15k.
引用
收藏
页码:258 / 267
页数:10
相关论文
共 32 条
  • [1] [Anonymous], 2014, P 2014 C EMPIRICAL M
  • [2] Bollacker K., 2008, P 2008 ACM SIGMOD IN, P1247
  • [3] Bordes Antoine, 2014, Machine Learning and Knowledge Discovery in Databases. European Conference, ECML PKDD 2014. Proceedings: LNCS 8724, P165, DOI 10.1007/978-3-662-44848-9_11
  • [4] Bordes A, 2013, ADV NEURAL INFORM PR, V26
  • [5] Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion
    Dong, Xin Luna
    Gabrilovich, Evgeniy
    Heitz, Geremy
    Horn, Wilko
    Lao, Ni
    Murphy, Kevin
    Strohmann, Thomas
    Sun, Shaohua
    Zhang, Wei
    [J]. PROCEEDINGS OF THE 20TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD'14), 2014, : 601 - 610
  • [6] An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge
    Hao, Yanchao
    Zhang, Yuanzhe
    Liu, Kang
    He, Shizhu
    Liu, Zhanyi
    Wu, Hua
    Zhao, Jun
    [J]. PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1, 2017, : 221 - 231
  • [7] He S., 2015, P 24 ACM INT C INF K, P623, DOI [10.1145/2806416.2806502, DOI 10.1145/2806416.2806502]
  • [8] Hoffmann Raphael, 2011, P 49 ANN M ASS COMP, P541
  • [9] Ji GL, 2016, AAAI CONF ARTIF INTE, P985
  • [10] Ji GL, 2015, PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, P687