Abstract
All automated coreference resolution systems consider a number of features, such as head noun, NP type, gender, or number. Although the particular features used is one of the key factors for determining performance, they have not received much attention, especially for languages other than English. This paper delves into a considerable number of pairwise comparison features for coreference, including old and novel features, with a special focus on the Spanish language. We consider the contribution of each of the features as well as the interaction between them. In addition, given the problem of class imbalance in coreference resolution, we analyze the effect of sample selection. From the experiments with TiMBL (Tilburg Memory-Based Learner) on the AnCora corpus, interesting conclusions are drawn from both linguistic and computational perspectives.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bengtson, E., Roth, D.: Understanding the value of features for coreference resolution. In: Proceedings of EMNLP, pp. 294–303 (2008)
Daelemans, W., Bosch, A.V.: Memory-Based Language Processing. Cambridge University Press, Cambridge (2005)
Hoste, V.: Optimization Issues in Machine Learning of Coreference Resolution. Ph.D thesis, University of Antwerp (2005)
Lappin, S., Leass, H.J.: An algorithm for pronominal anaphora resolution. Computational Linguistics 20(4), 535–561 (1994)
Luo, X., Ittycheriah, A., Jing, H., Kambhatla, N., Roukos, S.: A mention-synchronous coreference resolution algorithm based on the Bell tree. In: Proceedings of ACL, pp. 21–26 (2004)
McCarthy, J.F., Lehnert, W.G.: Using decision trees for coreference resolution. In: Proceedings of IJCAI, pp. 1050–1055 (1995)
Mitkov, R.: Robust pronoun resolution with limited knowledge. In: Proceedings of ACL-COLING, pp. 869–875 (1998)
Morton, T.S.: Using coreference in question answering. In: Proceedings of the 8th Text REtrieval Conference, pp. 85–89 (1999)
Ng, V., Cardie, C.: Improving machine learning approaches to coreference resolution. In: Proceedings of ACL, pp. 104–111 (2002)
Ponzetto, S.P., Strube, M.: Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In: Proceedings of HLT-NAACL, pp. 192–199 (2006)
Recasens, M., Martí, M.A.: AnCora-CO: Coreferentially annotated corpora for Spanish and Catalan. Language Resources and Evaluation (to appear)
Soon, W.M., Ng, H.T., Lim, D.C.Y.: A machine learning approach to coreference resolution of noun phrases. Computational Linguistics 27(4), 521–544 (2001)
Steinberger, J., Poesio, M., Kabadjov, M.A., Jeek, K.: Two uses of anaphora resolution in summarization. Information Processing and Management: an International Journal 43(6), 1663–1680 (2007)
Uryupina, O.: Knowledge Acquisition for Coreference Resolution. Ph.D thesis, Saarland University (2007)
Van Deemter, K., Kibble, R.: On coreferring: Coreference in MUC and related annotation schemes. Computational Linguistics 26(4), 629–637 (2000)
Yang, X., Su, J., Zhou, G., Tan, C.L.: Improving pronoun resolution by incorporating coreferential information of candidates. In: Proceedings of ACL, pp. 127–134 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Recasens, M., Hovy, E. (2009). A Deeper Look into Features for Coreference Resolution. In: Lalitha Devi, S., Branco, A., Mitkov, R. (eds) Anaphora Processing and Applications. DAARC 2009. Lecture Notes in Computer Science(), vol 5847. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04975-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-04975-0_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04974-3
Online ISBN: 978-3-642-04975-0
eBook Packages: Computer ScienceComputer Science (R0)