caa a22 4500 605470278 CHVBK 20210128100327.0 cr unu---uuuuu 210128e20150801xx s 000 0 eng 10.1007/s00500-014-1397-3 doi (NATIONALLICENCE)springer-10.1007/s00500-014-1397-3 Differential evolution-based feature selection technique for anaphora resolution [Elektronische Daten] [Utpal Sikdar, Asif Ekbal, Sriparna Saha, Olga Uryupina, Massimo Poesio] In this paper a differential evolution (DE)-based feature selection technique is developed for anaphora resolution in a resource-poor language, namely Bengali. We discuss the issues of adapting a state-of-the-art English anaphora resolution system for a resource-poor language like Bengali. Performance of any anaphoric resolver greatly depends on the quality of a high accurate mention detector and the use of appropriate features for anaphora resolution. We develop a number of models for mention detection based on machine learning and heuristics. In anaphora resolution there is no globally accepted metric for measuring the performance, and each of them such as MUC, $$\hbox {B}^{3}$$ B 3 , CEAF, Blanc exhibit significantly different behaviors. Our proposed feature selection technique determines the near-optimal feature set by optimizing each of these evaluation metrics. Experiments show how a language-dependent system (designed primarily for English) can attain reasonably good performance level when re-trained and tested on a new language with a proper subset of features. Evaluation results yield the F-measure values of 66.70, 59.47, 51.56, 33.08 and 72.75% for MUC, B 3, CEAFM, CEAFE and BLANC, respectively. Springer-Verlag Berlin Heidelberg, 2014 Anaphora resolution nationallicence Differential evolution nationallicence Feature selection nationallicence CRF nationallicence BART nationallicence Bengali nationallicence Sikdar Utpal Department of Computer Science and Engineering, IIT Patna, Patna, India aut Ekbal Asif Department of Computer Science and Engineering, IIT Patna, Patna, India aut Saha Sriparna Department of Computer Science and Engineering, IIT Patna, Patna, India aut Uryupina Olga Center for Mind/Brain Sciences, University of Trento, Trento, Italy aut Poesio Massimo School of Computing and Electronic Engineering, University of Essex, Colchester, UK aut Soft Computing Springer Berlin Heidelberg 19/8(2015-08-01), 2149-2161 1432-7643 19:8<2149 2015 19 500 https://doi.org/10.1007/s00500-014-1397-3 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00500-014-1397-3 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Sikdar Utpal Department of Computer Science and Engineering, IIT Patna, Patna, India aut NATIONALLICENCE 700 1- Ekbal Asif Department of Computer Science and Engineering, IIT Patna, Patna, India aut NATIONALLICENCE 700 1- Saha Sriparna Department of Computer Science and Engineering, IIT Patna, Patna, India aut NATIONALLICENCE 700 1- Uryupina Olga Center for Mind/Brain Sciences, University of Trento, Trento, Italy aut NATIONALLICENCE 700 1- Poesio Massimo School of Computing and Electronic Engineering, University of Essex, Colchester, UK aut NATIONALLICENCE 773 0- Soft Computing Springer Berlin Heidelberg 19/8(2015-08-01), 2149-2161 1432-7643 19:8<2149 2015 19 500