Elamur ResearchβŒ•
☰
home / papers / 2016 / Coreference in Wikipedia: Main Concept Resolution

Coreference in Wikipedia: Main Concept Resolution

Summary

Most coreference resolution (CR) systems are built for newswire and degrade on other genres, including Wikipedia. This work returns to a rarely explored task: locating every proper, nominal, and pronominal mention of an article's "main concept" (MC), meaning the entity the Wikipedia article is about. The authors treat it as binary classification, deciding for each detected mention whether it refers to the MC. They train separate pronominal and non-pronominal models. Features come from Wikipedia structure (internal hyperlinks, redirects, the title) and from Freebase attributes such as entity type, gender, and number. These signals replace an error-prone entity-linking step with human-made links. Evaluated on WikiCoref, the classifier clearly beats baselines that extract the MC chain from the output of state-of-the-art CR systems. Adding it as a high-precision first sieve in the Stanford rule-based system (Dcoref) also improves full coreference resolution. The work shows that Wikipedia's markup is a cheap and reliable source of knowledge for adapting CR to the encyclopedic genre.

Key points

  • Dataset: WikiCoref has 30 English Wikipedia articles (about 60k tokens) annotated under OntoNotes guidelines. Of roughly 7,000 non-singleton mentions, about 1,800 refer to the MC.
  • Genre gap: Existing systems lose substantial CoNLL F1 on WikiCoref compared with OntoNotes. For example, Scoref falls from 63.61 to 46.39. The rule-based Dcoref scores best on Wikipedia text (51.77).
  • Baselines: Four heuristic baselines (B1–B4) pick or merge coreference chains using chain length and matches with the article title.
  • MC classifier: The classifier reaches about 89% F1, which is 13 absolute points above the strongest baseline.
  • Full pipeline and resource: Dcoref++ lifts CoNLL F1 from 51.77 to 55.11 and improves on all three metrics (MUC, B3, CEAFΟ†4), with larger gains in precision than in recall. The authors also release a dump of MC mentions for all of English Wikipedia (April 2013 version).

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

Fields: Linguistics & languages

Topics: Coreference resolution

Cited by

8 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 5 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/k16-1023

@inproceedings{ghaddar2016coreference,
  title = {{Coreference in Wikipedia: Main Concept Resolution}},
  author = {Ghaddar, Abbas and Langlais, Phillippe},
  booktitle = {Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning},
  year = {2016},
  doi = {10.18653/v1/k16-1023},
  url = {https://doi.org/10.18653/v1/k16-1023}
}

References

39 references, 22 of them with a card of ours. β†— leads to the work, Β«findΒ» searches for one we have no id for yet.

  1. \#\# Conclusion Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The first international conference on language resources and evaluation workshop on linguistics coreference, volume 1, pages 563–566. find our card
  2. We developed a simple yet powerful approach that accurately identifies all the mentions that co-refer We use predicted results from 10-fold cross-validation. find
  3. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pages 1247–1250. find
  4. Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. OntoNotes: the 90% solution. In Proceedings of the human language technology conference of the NAACL, Companion Volume: Short Papers, pages 57–60. find
  5. Chih-Chung Chang and Chih-Jen Lin. 2011. LIB-SVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST), 2(3):27. find
  6. Heeyoung Lee, Angel Chang, Yves Peirsman, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics, 39(4):885–916. find our card
  7. Kevin Clark and Christopher D. Manning. 2015. Entity-centric coreference resolution with model stacking. In Association of Computational Linguistics (ACL). find our card
  8. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 25–32. find our card
  9. Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine learning, 20(3):273–297. find
  10. Pascal Denis and Jason Baldridge. 2009. Global joint models for coreference resolution and named entity classification. Procesamiento del Lenguaje Natural, 42(1):87–96. find
  11. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Rose Finkel, Steven Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP Natural Language Processing Toolkit. In ACL (System Demonstrations), pages 55–60. find our card
  12. George R. Doddington, Alexis Mitchell, Mark A. Przybocki, Lance A. Ramshaw, Stephanie Strassel, and Ralph M. Weischedel. 2004. The Automatic Content Extraction (ACE) Program-Tasks, Data, and Evaluation. In LREC, volume 2, page 1. find our card
  13. Sebastian Martschat and Michael Strube. 2015. Latent structures for coreference resolution. Transactions of the Association for Computational Linguistics, 3:405–418. find our card
  14. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In EMNLP, pages 1971–1982. find our card
  15. Olena Medelyan, David Milne, Catherine Legg, and Ian H. Witten. 2009. Mining meaning from wikipedia. Int. J. Hum.-Comput. Stud., 67(9):716– 754, September. find
  16. Greg Durrett and Dan Klein. 2014. A joint model for entity analysis: Coreference, typing, and linking. Transactions of the Association for Computational Linguistics, 2:477–490. find our card
  17. George A. Miller. 1995. WordNet: A Lexical Database for English. Commun. ACM, 38(11):39– 41. find our card
  18. David Milne and Ian H. Witten. 2008. Learning to link with wikipedia. In Proceedings of the 17th ACM conference on Information and knowledge management, pages 509–518. find
  19. Abbas Ghaddar and Phillippe Langlais. 2016. Wikicoref: An english coreference-annotated corpus of wikipedia articles. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2016). find our card
  20. Kotaro Nakayama. 2008. Wikipedia mining for triple extraction enhanced by co-reference resolution. In The 7th International Semantic Web Conference, page 103. find
  21. Aria Haghighi and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3-Volume 3, pages 1152–1161. find our card
  22. Vincent Ng. 2007. Shallow Semantics for Coreference Resolution. In IJcAI, volume 2007, pages 1689– 1694. find
  23. Hannaneh Hajishirzi, Leila Zilles, Daniel S. Weld, and Luke S. Zettlemoyer. 2013. Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves. In EMNLP, pages 289–299. find our card
  24. Dat PT Nguyen, Yutaka Matsuo, and Mitsuru Ishizuka. 2007. Relation extraction from wikipedia using subtree mining. In Proceedings of the National Conference on Artificial Intelligence, page 1414. find
  25. Iris Hendrickx and Veronique Hoste. 2009. Coreference resolution on blogs and commented news. In Anaphora Processing and Applications, pages 43– 53. find
  26. Simone Paolo Ponzetto and Michael Strube. 2006. Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, pages 192–… find our card
  27. Lynette Hirshman and Nancy Chinchor. 1998. MUC-7 coreference task definition. version 3.0. In Proceedings of the Seventh Message Understanding Conference (MUC-7). find our card
  28. Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 25–26. find
  29. Sameer S. Pradhan, Lance Ramshaw, Ralph Weischedel, Jessica MacBride, and Linnea Micciulla. 2007. Unrestricted coreference: Identifying entities and events in OntoNotes. In First IEEE International Conference on Semantic Computing, pages 446–453. find
  30. Jianping Zheng, Luke Vilnis, Sameer Singh, Jinho D. Choi, and Andrew McCallum. 2013. Dynamic knowledge-base alignment for coreference resolution. In Conference on Computational Natural Language Learning (CoNLL). find our card
  31. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL-Shared Task, pages 1– 40. find our card
  32. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pag… find our card
  33. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher Manning. 2010. A multi-pass sieve for coreference resolution. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 492–501. find our card
  34. Lev Ratinov and Dan Roth. 2012. Learning-based multi-sieve co-reference resolution with knowledge. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1234–1244. find our card
  35. Lev Ratinov, Dan Roth, Doug Downey, and Mike Anderson. 2011. Local and global algorithms for disambiguation to wikipedia. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, pages 1375–1384. find
  36. Ulrich Schäfer, Christian Spurk, and Jörg Steffen. 2012. A fully coreference-annotated corpus of scholarly papers from the acl anthology. In Proceedings of the 24th International Conference on Computational Linguistics (COLING-2012), pages 1059–1070. find our card
  37. Fabian M. Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. Yago: a core of semantic knowledge. In Proceedings of the 16th international conference on World Wide Web, pages 697–706. find
  38. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th conference on Message understanding, pages 45–52. find our card
  39. Alexander Yates, Michael Cafarella, Michele Banko, Oren Etzioni, Matthew Broadhead, and Stephen Soderland. 2007. Textrunner: open information extraction on the web. In Proceedings of Human find

↑ back to top