Elamur Research⌕
☰
home / papers / 2015 / Plato: A Selective Context Model for Entity Resolution

Plato: A Selective Context Model for Entity Resolution

Paper · 2015 · Nevena Lazic, Amarnag Subramanya, Michael Ringgaard et al.

Summary

Entity resolution links each mention in a text to the correct entry in a knowledge base (KB), or marks it NIL when no entry exists. A key difficulty is that most words around a mention say little about which entity is meant. Plato addresses this with a probabilistic "selective context" model, which extends naïve Bayes. Instead of treating all context features as evidence, it assumes a single feature is truly informative and that the others come from a background distribution. Under this assumption, an entity's score combines a name-based prior with a sum of feature scores that behave like pointwise mutual information. The model is first trained on labeled mentions taken from Wikipedia. It is then trained further with EM on a very large unlabeled Web corpus, which surfaces new useful features. The training runs in a distributed setup and handles KBs with more than 10^7 entities. The system was not tuned on any benchmark data, yet it performs at or near the state of the art on TAC KBP 2011, TAC KBP 2012 and CoNLL 2003. This shows that scalable semi-supervised learning can compete with more complex systems.

Key points

  • Plain naïve Bayes barely improves on the mention-prior baseline. The supervised selective context model, trained on the same Wikipedia data, does substantially better.
  • On TAC KBP 2011, Plato reaches the best in-KB accuracy (79.3). Its overall accuracy of 86.5 nearly matches Cucerzan (2011) at 86.8.
  • On TAC KBP 2012, Plato has the highest in-KB accuracy (74.2). Its overall accuracy of 76.6 ties the best earlier system, Cucerzan (2012).
  • Plato has no cross-entity coherency model. It uses simple within-document coreference clustering and adds the other referring phrases in the document as context features. Its accuracy on the full CoNLL dataset is 86.5.
  • Semi-supervised training fixes cases like "George Harrison" (Nintendo executive vs. the Beatle). Newly learned features such as Wii and Roush Fenway Racing raise the correct entity's probability from 0.02 to 0.74.

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

🏢GoogleMountain View · United States430 works · 424,363 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

Cite

Cite as Nevena Lazic, Amarnag Subramanya, Michael Ringgaard and Fernando Pereira. 2015. Plato: A Selective Context Model for Entity Resolution. 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_00154

@article{lazic2015plato,
  title = {{Plato: A Selective Context Model for Entity Resolution}},
  author = {Nevena Lazic, Amarnag Subramanya, Michael Ringgaard and Fernando Pereira},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2015},
  doi = {10.1162/tacl\_a\_00154},
  url = {https://doi.org/10.1162/tacl_a_00154}
}

References

41 references, 9 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 Proc. 52nd Annual Meeting of the Association for Computational Linguistics, ACL 14, pages 75–80. find
  2. Kurt D. Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proc. of the 2008 ACM SIGMOD International Conference on Management of Data, pages 1247–1250. find
  3. ACM. Razvan C. Bunescu and Marius Pasca. 2006. Using encyclopedic knowledge for named entity disambiguation. In Proc. 11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 06.
  4. Andrew Chisholm and Ben Hachey. 2015. Entity disambiguation with web links. Transactions of the Association for Computational Linguistics, 3:145–156.
  5. Silviu Cucerzan. 2007. Large-scale named entity disambiguation based on Wikipedia data. In Proc. of EMNLP-CoNLL 2007, pages 708–716. find
  6. Silviu Cucerzan. 2011. TAC entity linking by performing full-document entity extraction and disambiguation. In In Proc. of the Text Analysis Conference, TAC 11. find
  7. Silviu Cucerzan. 2012. The MSR system for entity linking at TAC 2012. In In Proc. of the Text Analysis Conference, TAC 12. find
  8. Jeffrey Dalton and Laura Dietz. 2013. A neighborhood relevance model for entity linking. In Proc. of the 10th Conference on Open Research Areas in Information Retrieval. find
  9. Jeffrey Dean and Sanjay Ghemawat. 2008. MapReduce: simplified data processing on large clusters. Communications of the ACM, 51(1):107–113, January. find
  10. Mark Dredze, Paul McNamee, Delip Rao, Adam Gerber, and Tim Finin. 2010. Entity disambiguation for knowledge base population. In Proc. of the 23rd International Conference on Computational Linguistics, COLING 10, pages 277–285.
  11. Paolo Ferragina and Ugo Scaiella. 2010. TAGME: on-the-fly annotation of short text fragments (by Wikipedia entities). In Proc. of the 19th ACM International Conference on Information Knowledge and Management, CIKM 10, pages 1625–1628. ACM.
  12. Tim Finin, Zareen Syed, James Mayfield, Paul Mc-Namee, and Christine Piatko. 2009. Using Wikitology for cross-document entity coreference resolution. In Proc. of the AAAI Spring Symposium on Learning by Reading and Learning to Read. find
  13. AAAI Press. Evgeniy Gabrilovich and Shaul Markovitch. 2007. Harnessing the expertise of 70,000 human editors: Knowledge-based feature generation for text categorization. Journal of Machine Learning Research, 8:2297–2345, December. find
  14. Ben Hachey, Will Radford, Joel Nothman, Matthew Honnibal, and James R. Curran. 2013. Evaluating entity linking with Wikipedia. Artificial Intelligence, 194(0):130 – 150. find
  15. Aria Haghighi and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Proc.of the 2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 09.
  16. ACL. Jamie Hallan and Mark Hoy. 2009. Clueweb09 data set. http://lemurproject.org/clueweb09/. ↗
  17. Xianpei Han and Le Sun. 2011. A generative entity-mention model for linking entities with knowledge base. In Proc. of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, volume 1 of ACLHLT 11. find
  18. ACL. Xianpei Han and Le Sun. 2012. An entity-topic model for entity linking. In EMNLP-CoNLL, pages 105–115. find
  19. Xianpei Han and Jun Zhao. 2009. Named entity disambiguation by leveraging Wikipedia semantic knowledge. In Proc. of the 18th Conference on Information and Knowledge Management, CIKM 09, pages 215– 224. find
  20. ACM. Xianpei Han, Le Sun, and Jun Zhao. 2011. Collective entity linking in Web text: a graph-based method. In In Proc. 34th ACM SIGIR conference on research and development in information retrieval, pages 765–774. find
  21. ACM. Zhengyan He, Shujie Liu, Mu Li, Ming Zhou, Longkai Zhang, and Houfeng Wang. 2013. Learning entity representation for entity disambiguation. In Proc. of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 13, pages 30–34. Johannes Hoffart, Mohamed Amir Yosef, Ilaria Bor… find
  22. Neil Houlsby and Massimiliano Ciaramita. 2014. A scalable Gibbs sampler for probabilistic entity linking. In Advances in Information Retrieval, pages 335–346. find
  23. Springer. Heng Ji, Ralph Grishman, and Hoa Trang Dang. 2011. Overview of the TAC 2011 knowledge base population track. In Proc. of the 4th Text Analysis Conference, TAC 11. find
  24. Yuzhe Jin, Emre Kiciman, Kuansan Wang, and Ricky Loynd. 2014. Entity linking at the tail: sparse signals, unknown entities, and phrase models. In Proc. of the 7th ACM International Conference on Web Search and Data Mining, WSDM ’14, pages 453–462, New York, NY, USA. find
  25. ACM. Saurabh S. Kataria, Krishnan S. Kumar, Rajeev R. Rastogi, Prithviraj Sen, and Srinivasan H. Sengamedu. 2011. Entity disambiguation with hierarchical topic models. In Proc. of the 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 1037–1045. find
  26. ACM. Sayali Kulkarni, Amit Singh, Ganesh Ramakrishnan, and Soumen Chakrabarti. 2009. Collective annotation of Wikipedia entities in web text. In Proc. of the 15th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 457–466. find
  27. ACM. Tom Kwiatkowski, Luke S. Zettlemoyer, Sharon Goldwater, and Mark Steedman. 2011. Lexical generalization in CCG grammar induction for semantic parsing. In Proc. of the 2011 Conference on Empirical Methods in Natural Language Processing, pages 1512–1523.
  28. Thomas Lin, Mausam, and Oren Etzioni. 2012. Entity linking at web scale. In Proc. of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction, AKBC-WEKEX ’12. find
  29. Mitchell P Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational linguistics, 19(2):313–330.
  30. James Mayfield, David Alexander, Bonnie Dorr, Jason Eisner, Tamer Elsayed, Tim Finin, Clay Fink, Marjorie Freedman, Nikesh Garera, Paul McNamee, Saif Mohammad, Douglas Oard, Christine Piatko, Asad Sayeed, Zareen Syed, Ralph Weischedel, Tan Xu, and David Yarowsky. 2009. Cross-document coreference res… find
  31. James Mayfield, Javier Artiles, and Hoa Trang Dang. 2012. Overview of the TAC 2012 knowledge base population track. In Proc. of the 5th Text Analysis Conference, TAC 12. find
  32. Rada Mihalcea and Andras Csomai. 2007. Wikify!: linking documents to encyclopedic knowledge. In Proc. of the 16th ACM Conference on Information and Knowledge Management, CIKM 07, pages 233–242. find
  33. David N. Milne and Ian H. Witten. 2008. Learning to link with Wikipedia. In Proc. of the 17th ACM Conference on Information and Knowledge Management, CIKM 07, pages 509–518. find
  34. Hien T. Nguyen and Tru H. Cao. 2008. Named entity disambiguation on an ontology enriched by Wikipedia. In Proc. 2008 IEEE International Conference on Research, Innovation, and Vision for the Future in Computing and Communication Technologies, RIVF 08, pages 247–254. find
  35. IEEE. Dat Ba Nguyen, Johannes Hoffart, Martin Theobald, and Gerhard Weikum. 2014. AIDA-light: High-throughput named-entity disambiguation. In Proc. of the Linked Data on the Web Workshop. find
  36. Kamal Nigam, Andrew Kachites McCallum, Sebastian Thrun, and Tom Mitchell. 2000. Text classification from labeled and unlabeled documents using EM. Machine Learning, 39(2-3):103–134, May. Joakim Nivre, Johan Hall, Jens Nilsson, Atanas Chanev, Gülsen Eryigit, Sandra Kübler, Svetoslav Marinov, and Er…
  37. Dave Orr, Amar Subramanya, and Fernando Pereira. 2013. Learning from big data: 40 million entities in context. http://googleresearch.blogspot.com/2013/03/ learning-from-big-data-40-million. html. ↗
  38. Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1999. The PageRank citation ranking: bringing order to the web. Technical Report SIDL-WP-1999-0120, Stanford InfoLab, November.
  39. Maria Pershina, Yifan He, and Ralph Grishman. 2015. Personalized Page Rank for named entity disambiguation. In Proc. 2015 Annual Conference of the North American Chapter of the ACL, NAACL HLT 14, pages 238–243. find
  40. Lev-Arie Ratinov, Dan Roth, Doug Downey, and Mike Anderson. 2011. Local and global algorithms for disambiguation to Wikipedia. In Proc. of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACLHLT 11, pages 1375–1384. find
  41. ACL. Avirup Sil and Alexander Yates. 2013. Re-ranking for joint named-entity recognition and linking. In Proc. of the 22nd ACM International Conference on Information & Knowledge Management, CIKM 13, pages 2369–2374. ACM. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lazic-2015-plato-selective-context-model-entity/