Natural Language Understanding Wiki

Entity linking (EL) is a similar but broader task than Named Entity Disambiguation (NED): NED is concerned with disambiguating a textual NE mention where the correct entity is known to be one of the KB entries, while EL also requires systems to deal with the case where there is no entry for the NE in the reference KB.[1]

3 general steps:

  1. mention detection
  2. link generation
  3. disambiguation


From Cheng and Roth (2013)[2]: "broad applications in NLP, Information Extraction, and Knowledge Acquisition from text, from coreference resolution (Ratinov and Roth, 2012) to entity linking and knowledge population (Ellis et al., 2011; Ji et al., 2010; Cucerzan, 2011)."


From Ling et al. (2015)[3]: "TAC11 and TAC12 [...] the organizers intentionally selected the mentions that are highly ambiguous such as “ABC” and/or incomplete such as “Brown”

State of the art[]

System KORE50 CoNLL
Babelfy[4] 71.5 82.1
KORE-LSH-G[5] 64.6 81.8
KORE[5] 63.9 80.7
Normalized Google Distance[6] 57.6 82.3
Tagme 2.0[7] 56.3 70.1
KPCS[5] 55.6 82.2
KORE-LSH-F[5] 53.2 81.2
UKB w2w (on BabelNet) 52.1 71.8
IllinoisWikifier[8] 41.7 72.4
DBpedia Spotlight 2011[9] 35.4 34.0

Further readings[]

  • Detecting unlinkable entities (Lin et al. 2012a)
  • Linking entities to any database (Sil et al. 2012)
  • Hyperlinking for multimedia data (Eskevich et al. 2013)
  • Automatically generating Wikipedia articles 
 (Sauper & Barzilay 2009)
  • Scaling up to the web (Lin et al. 2012b)
  • Serendipitous suggestions based on personalized entity links (Bordino et al. 2013)
  • Actionable entities/queries (Lin et al. 2012)



  1. Alhelbawy, A., & Gaizauskas, R. Collective Named Entity Disambiguation using Graph Ranking and Clique Partitioning Approaches.
  2. Cheng, X., & Roth, D. (2013). Relational Inference for Wikification. In EMNLP. Retrieved from
  3. Ling, X., Singh, S., & Weld, D. S. (2015). Design Challenges for Entity Linking. Transactions of the Association for Computational Linguistics, 3, 315–328. Retrieved from
  4. Moro, A., Raganato, A., & Navigli, R. (2014). Entity Linking meets Word Sense Disambiguation: A Unified Approach. Transactions of the Association for Computational Linguistics, 2, 231–244. Retrieved from
  5. 5.0 5.1 5.2 5.3 Johannes Hoffart, Stephan Seufert, Dat Ba Nguyen, Mar- tin Theobald, and Gerhard Weikum. 2012. KORE: keyphrase overlap relatedness for entity disambigua- tion. In Proc. of CIKM, pages 545–554.
  6. David Milne and Ian H. Witten. 2008. Learning to link withWikipedia. In Proc. of CIKM, pages 509–518.
  7. Paolo Ferragina and Ugo Scaiella. 2012. Fast and Accu- rate Annotation of Short Texts with Wikipedia Pages. IEEE Software, 29(1):70–75.
  8. Xiao Cheng and Dan Roth. 2013. Relational Inference for Wikification. In Proc. of EMNLP, pages 1787– 1796.
  9. Pablo N. Mendes, Max Jakob, Andr´ es Garc´ ıa-Silva, and Christian Bizer. 2011. DBpedia spotlight: shed- ding light on the web of documents. In Proc. of I- Semantics, pages 1–8.