Elamur Research⌕
☰
home / papers / 2015 / Entity Disambiguation with Web Links

Entity Disambiguation with Web Links

Paper · 2015 · Andrew Chisholm and Ben Hachey

Summary

Entity disambiguation systems usually depend on Wikipedia's curated structure: redirects, article text, inter-article links and categories. The authors ask whether ordinary web pages that hyperlink to Wikipedia can provide the same signals for a knowledge base without such curation. They build a benchmark linker from Wikipedia-derived data. They then build a second linker that obtains the same four model types only from about 34 million web links: an entity prior from in-link counts, name probabilities from anchors, textual context from text around links, and coherence from shared linking sources. Both are evaluated on the CoNLL (Yago2-annotated Reuters) and TAC 2010 data. The web-link linker reaches 93–100% of the Wikipedia linker's accuracy. Its context models are actually stronger. Combining both sources gives a new best of 88.7 p@1 on CoNLL test. The authors conclude that any knowledge base with enough incoming links could support entity linking. They argue that organisations should publish their authorities openly and invest in gathering links, not only in curation.

Key points

  • Evaluation uses precision@1 on CoNLL and KB accuracy on TAC 2010, following He et al. (2013), so candidate generation and mention detection do not affect the comparison.
  • Across configurations, web-link systems reach 93.1–100% of Wikipedia-based performance, about 97% on average.
  • Web-link context models beat Wikipedia context models by roughly 7–10 points. Web-link popularity and coherence models fall behind their Wikipedia counterparts.
  • Adding web-link features to the Wikipedia model raises CoNLL scores by about 4 points, reaching 88.7 p@1 and surpassing the earlier 87.6. On TAC 2010 the system scores 80.7, close to He et al.'s 81.0.
  • A simple coherence model adds 1–3 points, with no complex global graph inference required. The code is released under MIT at github.com/wikilinks/nel.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓The University of SydneySydney · Australia45 works · 68,350 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksDecision Sciences · 209 worksManagement Science and Operations Research · 108 works

🧭 Topics 1Research subjects and languages the work is about.Named entity recognition · 200 works

Cite

Cite as Andrew Chisholm and Ben Hachey. 2015. Entity Disambiguation with Web Links. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00129

@article{chisholm2015entity,
  title = {{Entity Disambiguation with Web Links}},
  author = {Andrew Chisholm and Ben Hachey},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2015},
  doi = {10.1162/tacl\_a\_00129},
  url = {https://doi.org/10.1162/tacl_a_00129}
}

References

34 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ayman Alhelbawy and Robert Gaizauskas. 2014. Graph ranking for collective named entity disambiguation. In Annual Meeting of the Association for Computational Linguistics, pages 75–80. Marco Baroni, Georgiana Dinu, and Germán Kruszewski. 2014. Don’t count, predict! a systematic comparison of context… find
  2. Yin-Wen Chang, Cho-Jui Hsieh, Kai-Wei Chang, Michael Ringgaard, and Chih-Jen Lin. 2010. Training and testing low-degree polynomial data mappings via linear SVM. Journal of Machine Learning Research, 11:1471–1490. find
  3. Silviu Cucerzan. 2011. TAC entity linking by performing full-document entity extraction and disambiguation. In Text Analysis Conference. find
  4. Jeffrey Dalton and Laura Dietz. 2013. UMass CIIR at TAC KBP 2013 entity linking: query expansion using Urban Dictionary. In Text Analysis Conference. find
  5. Paolo Ferragina and Ugo Scaiella. 2010. TAGME: On-the-fly annotation of short text fragments (by Wikipedia entities). In International Conference on Information and Knowledge Management, pages 1625–1628.
  6. Jiafeng Guo, Gu Xu, Xueqi Cheng, and Hang Li. 2009. Named entity recognition in query. In International Conference on Research and Development in Information Retrieval, pages 267–274. find
  7. Ben Hachey, Will Radford, Joel Nothman, Matthew Honnibal, and James R. Curran. 2013. Evaluating entity linking with Wikipedia. Artificial Intelligence, 194:130–150. find
  8. Ben Hachey, Joel Nothman, and Will Radford. 2014. Cheap and easy entity evaluation. In Annual Meeting of the Association for Computational Linguistics, pages 464–469. find
  9. Xianpei Han and Le Sun. 2011. A generative entity-mention model for linking entities with knowledge base. In Annual Meeting of the Association for Computational Linguistics, pages 945–954. find
  10. Xianpei Han, Le Sun, and Jun Zhao. 2011. Collective entity linking in web text: a graph-based method. In International Conference on Research and Development in Information Retrieval, pages 765–774. find
  11. Zhengyan He, Shujie Liu, Mu Li, Ming Zhou, Longkai Zhang, and Houfeng Wang. 2013. Learning entity representation for entity disambiguation. In Annual Meeting of the Association for Computational Linguistics, pages 30–34. Johannes Hoffart, Mohamed Amir Yosef, Ilaria Bordino, Hagen Fürstenau, Manfred… find
  12. Johannes Hoffart, Yasemin Altun, and Gerhard Weikum. 2014. Discovering emerging entities with ambiguous names. In International World Wide Web Conference, pages 385–396. find
  13. Heng Ji and Ralph Grishman. 2011. Knowledge base population: Successful approaches and challenges. In Annual Meeting of the Association for Computational Linguistics, pages 1148–1158. find
  14. Yuzhe Jin, Emre Kcman, Kuansan Wang, and Ricky Loynd. 2014. Entity linking at the tail: Sparse signals, unknown entities, and phrase models. In International Conference on Web Search and Data Mining, pages 453–462. find
  15. Thorsten Joachims. 2002. Optimizing search engines using clickthrough data. In International Conference on Knowledge Discovery and Data Mining, pages 133– 142. find
  16. Yang Li, Chi Wang, Fangqiu Han, Jiawei Han, Dan Roth, and Xifeng Yan. 2013. Mining evidences for named entity disambiguation. In International Conference on Knowledge Discovery and Data Mining, pages 1070– 1078. find
  17. Edgar Meij, Wouter Weerkamp, and Maarten de Rijke. 2012. Adding semantics to microblog posts. In International Conference on Web Search and Data Mining, pages 563–572. find
  18. Pablo N. Mendes, Max Jakob, and Christian Bizer. 2012. DBpedia: A multilingual cross-domain knowledge base. In International Conference on Language Resources and Evaluation, pages 1813–1817.
  19. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, pages 3111–3119.
  20. David Milne and Ian H. Witten. 2008. Learning to link with Wikipedia. In Conference on Information and Knowledge Management, pages 509–518. find
  21. Ndapandula Nakashole, Tomasz Tylenda, and Gerhard Weikum. 2013. Fine-grained semantic typing of emerging entities. In Annual Meeting of the Association for Computational Linguistics, pages 1488–1497. Máté Pataki, Miklós Vajna, and Attila Marosi. 2012. Wikipedia as text. ERCIM News, (89):48–49. find
  22. Fernando Pereira, Naftali Tishby, and Lillian Lee. 1993. Distributional clustering of English words. In Annual Meeting of the Association for Computational Linguistics, pages 183–190.
  23. Francesco Piccinno and Paolo Ferragina. 2014. From TagME to WAT: a new entity annotator. In SIGIR Workshop on Entity Recognition and Disambiguation, pages 55–62. find
  24. Will Radford, Will Cannings, Andrew Naoum, Joel Nothman, Glen Pink, Daniel Tse, and James R. Curran. 2012. (Almost) Total Recall – SYDNEY CMCRC at TAC 2012. In Text Analysis Conference. find
  25. Will Radford. 2014. Named entity linking using rich knowledge. Ph.D. thesis, The University of Sydney. find
  26. Lev Ratinov, Dan Roth, Doug Downey, and Mike Anderson. 2011. Local and global algorithms for disambiguation to Wikipedia. In Annual Meeting of the Association for Computational Linguistics, pages 1375– 1384. find
  27. Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information Processing and Management, 24(5):513– 523. find
  28. Wei Shan, Jiawei Han, and Jianyong Wang. 2014. A probabilistic model for linking named entities in web text with heterogeneous information networks. In International Conference on Mangement of Data, pages 1199–1210. find
  29. Wei Shen, Jianyon Wang, and Jiawei Han. 2014. Entity linking with a knowledge base: Issues, techniques, and solutions (to appear). Transactions on Knowledge and Data Engineering. find
  30. Clay Shirky. 2010. Cognitive surplus: Creativity and generosity in a connected age. find
  31. Allen Lane, London. Sameer Singh, Amarnag Subramanya, Fernando Pereira, and Andrew McCallum. 2012. Wikilinks: A large-scale cross-document coreference corpus labeled via links to Wikipedia. Technical Report UM-CS-2012-015, University of Massachusetts. find
  32. Merine Thomas, Hiroko Bretz, Thomas Vacek, Ben Hachey, Sudhanshu Singh, and Frank Schilder. 2014. Newton: Building an authority-driven company tagging and resolution system (in press). In Emma Tonkin and Stephanie Taylor, editors, Working With Text: Tools, techniques and approaches for text mining. find
  33. Chandos, Oxford, UK. Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Conference On Computational Natural Language Learning, pages 142–147.
  34. Vasudeva Varma, Praveen Bysani, Kranthi Reddy, Vijay Bharat, Santosh GSK, Karuna Kumar, Sudheer Kove-lamudi, Kiran Kumar N, and Nitin Maganti. 2009. IIIT Hyderabad at TAC 2009. In Text Analysis Conference. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chisholm-2015-entity-disambiguation-web-links/