Hunger for Contextual Knowledge and a Road Map to Intelligent Entity Linking

  • Filip Ilievski
  • Piek Vossen
  • Marieke van Erp
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10318)


The task of entity linking (EL) is often perceived as an algorithmic problem, where the novelty of systems lies in the decision making process, while the knowledge is relatively fixed. As a consequence, we lack an understanding about the importance and the relevance of diverse knowledge types in EL. However, knowledge and relevance are crucial: following the Gricean maxim, an author relies on assumptions about the knowledge of the reader and uses the most efficient and scarce, yet understandable, level of detail when conveying a message. In this paper, we seek to understand the EL task from a knowledge and relevance perspective. We define four categories of contextual knowledge relevant for EL and observe that two of these are systematically absent in existing entity linkers. Consequently, many contextual cases, in particular long-tail entities, can never be interpreted by existing systems. Finally, we present our ideas on developing knowledge-intensive systems and long-tail datasets.


Entity linking Context Long tail Knowledge Reasoning 



The research for this paper was supported by the Netherlands Organisation for Scientific Research (NWO) via the Spinoza fund and the CLARIAH-CORE project. We thank Stefan Schlobach, Frank van Harmelen, Eduard Hovy, and the reviewers for their ideas and input.


  1. 1.
    Cheng, X., Roth, D.: Relational inference for wikification. Urbana 51(61801), 16–58 (2013)Google Scholar
  2. 2.
    Daiber, J., Jakob, M., Hokamp, C., Mendes, P.N.: Improving efficiency and accuracy in multilingual entity extraction. In: Proceedings of SEMANTiCS, pp. 121–124. ACM (2013)Google Scholar
  3. 3.
    van Erp, M., Mendes, P., Paulheim, H., Ilievski, F., Plu, J., Rizzo, G., Waitelonis, J.: Evaluating entity linking: an analysis of current benchmark datasets and a roadmap for doing a better job. In: LREC, ELRA (2016)Google Scholar
  4. 4.
    Grice, P.: Logic and conversation. In: Cole, P., Morgan, J. (eds.) Syntax and Semantics, vol. 3, pp. 41–58. Academic Press, New York (1975)Google Scholar
  5. 5.
    Hovy, E.: Filling the long tail. In: Keynote Slides from the “Looking at the Long Tail” Workshop. VU Amsterdam (2016). Accessed 24 June 2016
  6. 6.
    Ilievski, F., Postma, M., Vossen, P.: Semantic overfitting: what world do we consider when evaluating disambiguation of text? In: Proceedings of COLING (2016)Google Scholar
  7. 7.
    Ilievski, F., Rizzo, G., van Erp, M., Plu, J., Troncy, R.: Context-enhanced adaptive entity linking. In: LREC 2016 (2016)Google Scholar
  8. 8.
    Ling, X., Singh, S., Weld, D.S.: Design challenges for entity linking. TACL 3, 315–328 (2015)Google Scholar
  9. 9.
    MacLachlan, G., Reid, I.: Framing and Interpretation. Melbourne University Press, Portland (1994)Google Scholar
  10. 10.
    Moro, A., Raganato, A., Navigli, R.: Entity linking meets word sense disambiguation: a unified approach. TACL 2, 231–244 (2014)Google Scholar
  11. 11.
    Narasimhan, K., Yala, A., Barzilay, R.: Improving information extraction by acquiring external evidence with reinforcement learning (2016)Google Scholar
  12. 12.
    Nguyen, T.H., Fauceglia, N., Muro, M.R., Hassanzadeh, O., Gliozzo, A.M., Sadoghi, M.: Joint learning of local and global features for entity linking via neural networks. In: Proceedings of COLING (2016)Google Scholar
  13. 13.
    Postma, M., Izquierdo, R., Agirre, E., Rigau, G., Vossen, P.: Addressing the MFS bias in WSD systems. In: Proceedings of LREC 2016, ELRA, France (2016)Google Scholar
  14. 14.
    Tristram, F., Walter, S., Cimiano, P., Unger, C.: Weasel: a machine learning based approach to entity linking combining different features. In: Proceedings of 3rd International Workshop on NLP and DBpedia, ISWC 2015 (2015)Google Scholar
  15. 15.
    Usbeck, R., Ngonga Ngomo, A.-C., Röder, M., Gerber, D., Coelho, S.A., Auer, S., Both, A.: AGDISTIS - graph-based disambiguation of named entities using linked data. In: Mika, P., et al. (eds.) ISWC 2014. LNCS, vol. 8796, pp. 457–471. Springer, Cham (2014). doi: 10.1007/978-3-319-11964-9_29 Google Scholar
  16. 16.
    Vossen, P., Agerri, R., Aldabe, I., Cybulska, A., van Erp, M., Fokkens, A., Laparra, E., Minard, A.L., Aprosio, A.P., Rigau, G., Rospocher, M., Segers, R.: NewsReader: using knowledge resources in a cross-lingual reading machine to generate more knowledge from massive streams of news. Special Issue Knowledge-Based Systems, Elsevier (2016)Google Scholar
  17. 17.
    Zwicklbauer, S., Seifert, C., Granitzer, M.: DoSeR - a knowledge-base-agnostic framework for entity disambiguation using semantic embeddings. In: Sack, H., Blomqvist, E., d’Aquin, M., Ghidini, C., Ponzetto, S.P., Lange, C. (eds.) ESWC 2016. LNCS, vol. 9678, pp. 182–198. Springer, Cham (2016). doi: 10.1007/978-3-319-34129-3_12 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Vrije Universiteit AmsterdamAmsterdamThe Netherlands

Personalised recommendations