Elamur Research⌕
☰
home / papers / 2013 / Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves

Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves

Summary

Coreference resolvers often fail because they lack background knowledge about entities. Named-entity linking (NEL) systems, in turn, frequently misjudge context when they examine each mention in isolation. The authors argue that the two tasks can help each other and propose NECO, a deterministic joint system with no training phase. NECO builds on the Stanford multi-pass sieve coreference resolver in four ways:

  • It pools candidate mentions from Stanford's detector and from two NEL systems, GLOW and WikipediaMiner, keeping only high-confidence links from their ensemble.
  • It attaches coarse and fine-grained attributes from Freebase and Wikipedia to linked mentions.
  • It blocks cluster merges whose entity links conflict.
  • It adds two new sieves that use NEL information.

As clusters grow, links and attributes spread from easy mentions to harder ones, such as a bare surname. Experiments on ACE 2004 and CoNLL 2011 show gains on both tasks, with gold and with automatically detected mentions. The work shows that joint modeling of entity identity improves results on both tasks, and the authors release their code and a new NEL-annotated corpus.

Key points

  • On ACE 2004 newswire, NECO cuts MUC coreference error by more than 11% and NEL F1 error by nearly 21%. MUC recall on this data rises by 6.2 points.
  • On the CoNLL 2011 test set, MUC precision improves by 3.1 points over the Stanford sieve system, which won the CoNLL 2011 shared task.
  • On a newly labeled test set, NEL F1 rises from 61.7% to 69.2%.
  • The system draws semantic attributes from Freebase and Wikipedia, using over 500 fine-grained types (e.g., president, park, country) plus coarse NER, gender and type classes.
  • In the error analysis, the largest remaining error sources are extra mentions (31.1%) and pronouns (27.7%). Semantic and attribute gaps account for the rest.

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

Fields: Linguistics & languages

Topics: Named entity recognition · Coreference resolution

Cited by

25 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 18 not yet.

Cite

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

@inproceedings{hajishirzi2013joint,
  title = {{Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves}},
  author = {Hajishirzi, Hannaneh and Zilles, Leila and Weld, Daniel S. and Zettlemoyer, Luke},
  booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing},
  year = {2013},
  doi = {10.18653/v1/d13-1029},
  url = {https://doi.org/10.18653/v1/d13-1029}
}

References

27 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference. find our card
  2. Mohit Bansal and Dan Klein. 2012. Coreference semantics from web features. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics. find our card
  3. Hal Daumé III and Daniel Marcu. 2005. A large-scale exploration of effective global features for a joint entity detection and tracking model. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing. find
  4. Stephen Dill, Nadav Eiron, David Gibson, Daniel Gruhl, R. Guha, Anant Jhingran, Tapas Kanungo, Sridhar Rajagopalan, Andrew Tomkins, John A. Tomlin, and Jason Y. Zien. 2003. SemTag and Seeker: bootstrapping the semantic web via automated semantic annotation. In Proceedings of the 12th International C… find
  5. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. find our card
  6. Jenny Rose Finkel and Christopher D. Manning. 2008. Enforcing transitivity in coreference resolution. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies. find our card
  7. Ben Hachey, Will Radford, Joel Nothman, Matthew Honnibal, and James R. Curran. 2013. Evaluating entity linking with Wikipedia. Artificial Intelligence Journal, 194. find
  8. Aria Haghighi and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. find our card
  9. Aria Haghighi and Dan Klein. 2010. Coreference resolution in a modular, entity-centered model. In Human Language Technologies: Annual Conference of the North American Chapter of the Association for Computational Linguistics. find our card
  10. Dan Klein and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics. find our card
  11. Sayali Kulkarni, Amit Singh, Ganesh Ramakrishnan, and Soumen Chakrabarti. 2009. Collective annotation of Wikipedia entities in Web text. In Proceedings of the 2009 Conference on Knowledge Discovery and Data Mining. find
  12. Heeyoung Lee, Yves Peirsman, Angel Chang, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2011. Stanford’s multi-pass sieve coreference resolution system at the CoNLL-2011 shared task. In Proceedings of the Conference on Computational Natural Language Learning. find our card
  13. 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). find our card
  14. Dan Milne and Ian H. Witten. 2008. Learning to link with Wikipedia. In Proceedings of the ACM Conference on Information and Knowledge Management. find
  15. Vincent Ng. 2007. Shallow semantics for coreference resolution. In Proceedings of the 20th International Joint Conference on Artificial Intelligence. find
  16. Vincent Ng. 2010. Supervised noun phrase coreference research: The first fifteen years. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. find our card
  17. NIST. 2004. The ACE 2004 evaluation planXPToolkit architecture. find
  18. Simone Paolo Ponzetto and Michael Strube. 2006. Exploiting semantic role labeling, Wordnet and Wikipedia for coreference resolution. In Proceedings of the North American Association for Natural Language Processing on Human Language Technologies. find our card
  19. Hoifung Poon and Pedro Domingos. 2008. Joint unsupervised coreference resolution with Markov logic. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. find our card
  20. Sameer Pradhan, Lance Ramshaw, Mitchell Marcus, Martha Palmer, Ralph Weischedel, and Nianwen Xue. 2011. CoNLL-2011 shared task: modeling unrestricted coreference in OntoNotes. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task. find our card
  21. 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 Conference on Empirical Methods in Natural Language Processing. find our card
  22. Altaf Rahman and Vincent Ng. 2011. Coreference resolution with world knowledge. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. find our card
  23. Lev Ratinov and Dan Roth. 2012. Learning-based multi-sieve co-reference resolution with knowledge. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. find our card
  24. 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. find
  25. Marta Recasens and Eduard Hovy. 2010. Coreference resolution across corpora: languages, coding schemes, and preprocessing information. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. find our card
  26. 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. find our card
  27. Jiaping Zheng, Luke Vilnis, Sameer Singh, Jinho D. Choi, and Andrew McCallum. 2013. Dynamic knowledge-base alignment for coreference resolution. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning. find our card

↑ back to top

This page in Markdown →