Collective Entity Linking on Relational Graph Model with Mentions

  • Jing Gong
  • Chong FengEmail author
  • Yong Liu
  • Ge Shi
  • Heyan Huang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10565)


Given a source document with extracted mentions, entity linking calls for mapping the mention to an entity in reference knowledge base. Previous entity linking approaches mainly focus on generic statistic features to link mentions independently. However, additional interdependence among mentions in the same document achieved from relational analysis can improve the accuracy. This paper propose a collective entity linking model which effectively leverages the global interdependence among mentions in the same source document. The model unifies semantic relations and co-reference relations into relational inference for semantic information extraction. Graph based linking algorithm is utilized to ensure per mention with only one candidate entity. Experiments on datasets show the proposed model significantly out-performs the state-of-the-art relatedness approaches in term of accuracy.


Collective entity linking Entity disambiguation Relational graph 



The research of this paper is partially supported by National 863 project 2015AA015404 and open project of State key lab. Smart manufacturing for special vehicles and transmission system.


  1. 1.
    Ji, H., Grishman, R., Dang, H.T., et al.: Overview of the TAC 2010 knowledge base population track. In: Text Analysis Conference (2010)Google Scholar
  2. 2.
  3. 3.
    Ji, H., Grishman, R.: Knowledge base population: successful approaches and challenges. In: Proceedings of ACL, Portland, Oregon, USA, 19–24 June 2011Google Scholar
  4. 4.
    Ratinov, L., Dan, R., Downey, D., et al.: Local and global algorithms for disambiguation to Wikipedia. In: Proceedings of ACL, Portland, Oregon, USA, 19–24 June 2011, pp. 1375–1384 (2011)Google Scholar
  5. 5.
    Fader, A., Soderland, S., Etzioni, O.: Scaling Wikipedia-based named entity disambiguation to arbitrary web text. In: Proceedings of Wikiai (2009)Google Scholar
  6. 6.
    Cucerzan, S.: TAC entity linking by performing full-document entity extraction and disambiguation. In: 2011 Proceedings of the Text Analysis Conference (2011)Google Scholar
  7. 7.
    Milne, D., Witten, I.H.: Learning to link with Wikipedia. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management, pp. 509–518. ACM (2008)Google Scholar
  8. 8.
    Dutta, S., Weikum, G.: C3EL: a joint model for cross-document co-reference resolution and entity linking. In: Proceedings of EMNLP (2015)Google Scholar
  9. 9.
    Zheng, J., Vilnis, L., Singh, S., et al.: Dynamic knowledge-base alignment for coreference resolution. In: Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pp. 153–162 (2013)Google Scholar
  10. 10.
    Navigli, R., Lapata, M.: An experimental study of graph connectivity for unsupervised word sense disambiguation. IEEE Trans. Pattern Anal. Mach. Intell. 32(4), 678–692 (2010)CrossRefGoogle Scholar
  11. 11.
    Blanco, R., Boldi, P., Marino, A.: Using graph distances for named-entity linking. Sci. Comput. Program. 130, 24–36 (2015)CrossRefGoogle Scholar
  12. 12.
    Aharonu, M., Kale, M.R.: Entity linking based graph models for Wikipedia relationships. Int. J. Eng. Trends Technol. 18(8), 380–385 (2014)CrossRefGoogle Scholar
  13. 13.
    Han, X., Sun, L., Zhao, J.: Collective entity linking in web text: a graph-based method. In: SIGIR, pp. 765–774. ACM (2011)Google Scholar
  14. 14.
    Qiao, L., Yun, Z., Yang, L., et al.: Graph-based collective chinese entity linking algorithm. J. Comput. Res. Dev. (2016)Google Scholar
  15. 15.
    Chan, Y.S., Roth, D.: Exploiting syntactico-semantic structures for relation extraction. In: Proceedings of ACL: Proceedings of the Conference on Human Language Technologies, Portland, Oregon, USA, 19–24 June 2011, pp. 551–560 (2011)Google Scholar
  16. 16.
    Sozio, M., Gionis, A.: The community-search problem and how to plan a successful cocktail party. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 939–948. ACM (2010)Google Scholar
  17. 17.
    Cheng, X., Roth, D.: Relational inference for Wikification. In: Proceedings of EMNLP, pp. 1787–1796. ACL (2013)Google Scholar
  18. 18.
    Hoffart, J., Yosef, M.A., Bordino, I., et al.: Robust disambiguation of named entities in text. In: Proceedings of EMNLP, pp. 782–792. ACL (2011)Google Scholar
  19. 19.
    Flanigan, J., Thomson, S., Carbonell, J., et al.: A discriminative graph-based parser for the abstract meaning representation. In: Proceedings of ACL, pp. 1426–1436 (2014)Google Scholar
  20. 20.
    Ji, H., Nothman, J., Hachey, B.: Overview of TAC-KBP2014 entity discovery and linking tasks. In: Proceedings of Text Analysis Conference (TAC 2014), November 2014Google Scholar
  21. 21.
    Lin, Y., Lin, C.-Y., Ji, H.: List-only entity linking. In: Proceedings of ACL, pp. 536–541 (2017)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Jing Gong
    • 1
  • Chong Feng
    • 1
    Email author
  • Yong Liu
    • 2
  • Ge Shi
    • 1
  • Heyan Huang
    • 1
  1. 1.Beijing Institute of Technology UniversityBeijingChina
  2. 2.State Key LabBeijingChina

Personalised recommendations