Abstract
In this paper we propose a multiobjective simulated annealing based technique for anaphora resolution. There is no generally accepted metric for measuring the performance of anaphora resolution systems, and the existing metrics–MUC, B3 , CEAF, Blanc, among others–tend to reward significantly different behaviors. Systems optimized according to one metric tend to perform poorly with respect to other ones, making it very difficult to compare anaphora resolution systems, as clearly shown by the results of the SEMEVAL 2010 Task 1 on the Multilingual Coreference Resolution. One solution would be to find a single completely satisfactory metric, but its not clear whether this is possible and at any rate it is not going to happen any time soon. An alternative is to optimize models according to multiple metrics simultaneously. In this paper, we propose a multiobjective simulated annealing based technique to solve the feature selection problem of anaphora resolution by optimizing multiple objective functions. Experimental results show that the proposed approach performs superior in comparison to the previously developed multiobjective genetic algorithm based feature selection technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bagga, A., Baldwin, B.: Algorithms for scoring coreference chains. In: LREC Workshop on Linguistic Coreference, pp. 563–566 (1998)
Bandyopadhyay, S., Saha, S., Maulik, U., Deb, K.: A simulated annealing based multi-objective optimization algorithm: AMOSA. IEEE Transactions on Evolutionary Computation 12(3), 269–283 (2008)
Bengtson, E., Roth, D.: Understanding the value of features for coreference resolution. In: EMNLP (2008)
Deb, K.: Multi-objective Optimization Using Evolutionary Algorithms. John Wiley and Sons, Ltd., England (2001)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6(2), 181–197 (2002)
Doddington, G., Mitchell, A., Przybocki, M., Ramshaw, L., Strassell, S., Weischedel, R.: The automatic content extraction (ACE) program-tasks, data, and evaluation. In: LREC (2000)
Hoste, V.: Optimization Issues in Machine Learning of Coreference Resolution. Ph.D. thesis, Antwerp University (2005)
Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220, 671–680 (1983)
Luo, X.: On coreference resolution performance metrics. In: NAACL / EMNLP, Van-couver (2005)
Metropolis, N., Rosenbluth, A.W., Rosenbloth, M.N., Teller, A.H., Teller, E.: Equation of state calculation by fast computing machines. J. Chemical Physics 21(6), 1087–1092 (1953)
Munson, A., Cardie, C., Caruana, R.: Optimizing to arbitrary NLP metrics using ensembleselection. In: HLT/EMNLP, pp. 539–546 (2005)
Ng, V., Cardie, C.: Improving machine learning approaches to coreference resolution. In: ACL, pp. 104–111 (2002)
Poon, H., Domingos, P.: Joint unsupervised coreference resolution with Markov logic. In: EMNLP (2008)
Pradhan, S., Marcus, M., Palmer, M., Ramshaw, L., Weischedel, R., Xue, N.: Conll-2011:Shared task on modeling unrestricted coreference in ontonotes, Portland, Oregon, USA, June23-24 (2011), http://www.cnts.ua.ac.be/conll/
Recasens, M., Hovy, E.: A Deeper Look into Features for Coreference Resolution. In: Lalitha Devi, S., Branco, A., Mitkov, R. (eds.) DAARC 2009. LNCS, vol. 5847, pp. 29–42. Springer, Heidelberg (2009)
Recasens, M., Hovy, E.: Blanc: Implementing the rand index for coreference evaluation. Natural Language Engineering (2011)
Recasens, M., Márquez, L., Sapena, E., Mart, M.A., Taul, M., Hoste, V., Poesio, M., Ver-rsley, Y.: Semeval-2010 task 1: Coreference resolution in multiple languages. In: SE-MEVAL 2010, Uppsala (2010)
Saha, S., Ekbal, A., Uryupina, O., Poesio, M.: Single and multi-objective optimization forfeature selection in anaphora resolution. In: IJCNLP (2011)
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)
Uryupina, O.: Knowledge Acquisition for Coreference Resolution. Ph.D. thesis, University of the Saarland (2007)
Uryupina, O.: Corry: a system for coreference resolution. In: SemEval (2010)
Veldhuizen, D.V., Lamont, G.: Multiobjective evolutionary algorithms: Analyzing the state-of-the-art. Evolutionary Computations 2, 125–1473 (2000)
Versley, Y., Ponzetto, S.P., Poesio, M., Eidelman, V., Jern, A., Smith, J., Yang, X., Moschitti, A.: BART: a modular toolkit for coreference resolution. In: ACL/HLT, pp. 9–12 (2008)
Vilain, M., Burger, J., Aberdeen, J., Connolly, D., Hirschman, L.: A model-theoretic coreference scoring scheme. MUC 6, 45–52 (1995)
Zhao, S., Ng, H.T.: Maximum metric score training for coreference resolution. In: COLING 2010 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ekbal, A., Saha, S., Uryupina, O., Poesio, M. (2011). Multiobjective Simulated Annealing Based Approach for Feature Selection in Anaphora Resolution. In: Hendrickx, I., Lalitha Devi, S., Branco, A., Mitkov, R. (eds) Anaphora Processing and Applications. DAARC 2011. Lecture Notes in Computer Science(), vol 7099. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25917-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-25917-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25916-6
Online ISBN: 978-3-642-25917-3
eBook Packages: Computer ScienceComputer Science (R0)