Elamur Research⌕
☰
home / papers / 2013 / Dynamic Knowledge-Base Alignment for Coreference Resolution

Dynamic Knowledge-Base Alignment for Coreference Resolution

Summary

Coreference systems often lack the world knowledge needed to connect mentions such as a politician's name and a descriptive title. Earlier work brought in external knowledge bases by fixing each mention's alignment before coreference began. These systems either kept only confident links, which produced few matches, or pooled many candidates, which blended distinct entities. Zheng et al. instead perform entity linking and within-document coreference together. Each proper-noun mention gets a scored list of Wikipedia candidates from the Dalton and Dietz (2013) KB searcher. Every candidate is enriched with web anchor texts that point to it (Spitkovsky and Chang, 2012), which supplies many name variants. Inference uses a pairwise SVM classifier with BestLink. Comparisons draw features from the antecedent's current top-ranked candidate. When two mentions are joined, their candidate lists are merged and reranked, so early alignment errors can be corrected. On ACE 2004 the method sets a new state of the art in B3 F1, including on transcripts and mention-dense documents. Keeping the alignment flexible lets external knowledge help a wider range of mentions.

Key points

  • On ACE 2004, the method gains 1.09 B3 F1 over the authors' knowledge-free baseline and 0.41 B3 F1 over the earlier best system (Stoyanov and Eisner, 2012).
  • The baseline follows Bengston and Roth (2008) with extra features (string match, distance, head POS tags). It also adds three changes:
    • a hinge-loss, L2-regularized SVM instead of an averaged perceptron;
    • pairwise features merged from already-coreferent mentions;
    • negative-example pruning using the k closest coreferent antecedents.
  • Name variants for each candidate entity come from web-wide anchor texts linking to the corresponding Wikipedia article.
  • Unlike Ratinov and Roth (2012), the evaluation covers the full ACE mention set, including the harder transcript documents.
  • On a larger multi-genre set of 2083 documents, B3 F1 rises from 65.3 (baseline) to 67.6 (static linking) and 67.7 (dynamic linking). The dynamic system beats all but two closed-task participants.

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: Coreference resolution

Cited by

9 papers of our library cite it (of the 140673 whose bibliographies we read); 6 of them have a page here, 3 not yet.

Cite

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

@inproceedings{zheng2013dynamic,
  title = {{Dynamic Knowledge-Base Alignment for Coreference Resolution}},
  author = {Zheng, Jiaping and Vilnis, Luke and Singh, Sameer and Choi, Jinho D. and McCallum, Andrew},
  booktitle = {Proceedings of the Seventeenth Conference on Computational Natural Language Learning},
  year = {2013},
  url = {https://aclanthology.org/W13-3517/}
}

References

31 references, 18 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 (LREC) Workshop on Linguistics Coreference, pages 563–566. find our card
  2. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The berkeley framenet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, ACL ’98, pages 86–90, Stroudsburg, PA, US… find our card
  3. Eric Bengston and Dan Roth. 2008. Understanding the value of features for coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP). find our card
  4. 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, SIGMOD ’08, pages 1247–1250, New York, NY, USA.… find
  5. Silviu Cucerzan. 2007. Large-scale named entity disambiguation based on Wikipedia data. In Empirical Methods in Natural Language Processing (EMNLP), pages 708–716. find
  6. Aron Culotta, Michael Wick, and Andrew McCallum. 2007. First-order probabilistic models for coreference resolution. In North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT). find our card
  7. Jeffrey Dalton and Laura Dietz. 2013. A neighborhood relevance model for entity linking. In Open Research Areas in Information Retrieval (OAIR). find
  8. Laura Dietz and Jeffrey Dalton. 2012. Across-document neighborhood expansion: UMass at TAC KBP 2012 entity linking. In Text Analysis Conference (TAC). find
  9. G. Doddington, A. Mitchell, M. Przybocki, L. Ramshaw, S. Strassel, and R. Weischedel. 2004. The Automatic Content Extraction (ACE) program–tasks, data, and evaluation. In Proceedings of LREC, volume 4, pages 837–840. find our card
  10. Tim Finin, Zareen Syed, James Mayfield, Paul Mc-Namee, and Christine Piatko. 2009. Using Wikitology for cross-document entity coreference resolution. In AAAI Spring Symposium on Learning by Reading and Learning to Read. find
  11. Aria Haghighi and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Empirical Methods in Natural Language Processing (EMNLP), pages 1152–1161. find our card
  12. Aria Haghighi and Dan Klein. 2010. Coreference resolution in a modular, entity-centered model. In North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), pages 385–393. find our card
  13. Xianpei Han and Jun Zhao. 2009. Named entity disambiguation by leveraging Wikipedia semantic knowledge. In Conference on Information and Knowledge Management (CIKM), pages 215–224. find
  14. Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke Zettlemoyer, and Daniel S. Weld. 2011. Knowledge-based weak supervision for information extraction of overlapping relations. In Annual Meeting of the Association for Computational Linguistics (ACL), pages 541–550, Portland, Oregon, USA, June. Associati… find
  15. 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 Conference on Computational Natural Language Learning (CoNLL), pages 28–34. Association for Computational… find our card
  16. Vincent Ng and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Annual Meeting of the Association for Computational Linguistics (ACL), pages 104–111. find our card
  17. 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, ACL ’10, pages 1396– 1411, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  18. Simone Paolo Ponzetto and Michael Strube. 2006. Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT), pages 192–199. find our card
  19. Sameer Pradhan, Lance Ramshaw, Mitchell Marcus, Martha Palmer, Ralph Weischedel, and Nianwen Xue. 2011. CoNLL-2011 shared task: Modeling unrestricted coreference in ontonotes. In Conference on Computational Natural Language Learning (CoNLL), pages 1–27. find our card
  20. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher Manning. 2010. A multi-pass sieve for coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP), pages 492–501. Association for Computational Linguisti… find our card
  21. Altaf Rahman and Vincent Ng. 2011. Coreference resolution with world knowledge. In Annual Meeting of the Association for Computational Linguistics (ACL), pages 814–824, Portland, Oregon, USA, June. find our card
  22. L. Ratinov and D. Roth. 2012. Learning-based multi-sieve co-reference resolution with knowledge. In Empirical Methods in Natural Language Processing (EMNLP). find our card
  23. L. Ratinov, D. Roth, D. Downey, and M. Anderson. 2011. Local and global algorithms for disambiguation to wikipedia. In Annual Meeting of the Association for Computational Linguistics (ACL). find
  24. Sebastian Riedel, Limin Yao, and Andrew McCallum. 2010. Collective cross-document relation extraction without labelled data. In Empirical Methods in Natural Language Processing (EMNLP). find
  25. Sameer Singh, Michael L. Wick, and Andrew McCallum. 2010. Distantly labeling data for large scale cross-document coreference. Computing Research Repository (CoRR), abs/1005.4298. — [arXiv:1005.4298](https://arxiv.org/abs/1005.4298) find
  26. Wee Meng Soon, Hwee Tou Ng, and Daniel Chung Yong Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521–544, Dec. find our card
  27. Valentin I. Spitkovsky and Angel X. Chang. 2012. A cross-lingual dictionary for english wikipedia concepts. In International Conference on Language Resources and Evaluation (LREC). find
  28. Veselin Stoyanov and Jason Eisner. 2012. Easy-first coreference resolution. In Computational Linguistics (COLING). find our card
  29. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010. Coreference resolution with reconcile. In Annual Meeting of the Association for Computational Linguistics (ACL), pages 156–161, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  30. 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, WWW ’07, pages 697– 706, New York, NY, USA. ACM. find
  31. Michael Wick, Aron Culotta, Khashayar Rohanimanesh, and Andrew McCallum. 2009. An entity-based model for coreference resolution. In SIAM International Conference on Data Mining (SDM). find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zheng-2013-dynamic-knowledge-base-alignment-coreference/