A Combined Memory-Based Semantic Role Labeler of English

CoNLL 2008: Proceedings of the 12th Conference on Computational Natural Language Learning, pages 208–212 Manchester, August 2008 A Combined Memory-Based Semantic Role Labeler of English Roser Morante, Walter Daelemans, Vincent Van Asch CNTS - Language Technology Group University of Antwerp Prinsstraat 13, B-2000 Antwerpen, Belgium {Roser.Morante,Walter.Daelemans,Vincent.VanAsch}@ua.ac.be Abstract We describe the system submitted to the closed challenge of the CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies. Syntactic de- pendencies are processed with the Malt- Parser 0.4. Semantic dependencies are processed with a combination of memory- based classifiers. The system achieves 78.43 labeled macro F1 for the complete problem, 86.07 labeled attachment score for syntactic dependencies, and 70.51 la- beled F1 for semantic dependencies. 1 Introduction In this paper we describe the system submitted to the closed challenge of the CoNLL-2008 shared task on joint parsing of syntactic and semantic de- pendencies (Surdeanu et al., 2008). Compared to the previous shared tasks on semantic role label- ing, the innovative feature of this one is that it consists of extracting both syntactic and seman- tic dependencies. The semantic dependencies task comprises labeling the semantic roles of nouns and verbs and disambiguating the frame of predicates. The system that we present extracts syntactic and semantic dependencies independently. Syn- tactic dependencies are processed with the Malt- Parser 0.4 (Nivre, 2006; Nivre et al., 2007). Se- mantic dependencies are processed with a combi- nation of memory-based classifiers. Memory-based language processing (Daele- mans and van den Bosch, 2005) is based on the c⃝ 2008. Licensed under the Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported li- cense (http://creativecommons.org/licenses/by-nc-sa/3.0/). Some rights reserved. idea that NLP problems can be solved by stor- ing solved examples of the problem in their literal form in memory, and applying similarity-based reasoning on these examples in order to solve new ones. Keeping literal forms in memory has been argued to provide a key advantage over abstracting methods in NLP that ignore exceptions and sub- regularities (Daelemans et al., 1999). Memory-based algorithms have been previously applied to semantic role labeling. Van den Bosch et al. (2004) participated in the CoNLL- 2004 shared task with a system that extended the basic memory-based learning method with class n-grams, iterative classifier stacking, and automatic output post-processing. Tjong Kim Sang et al. (2005) participated in the CoNLL- 2005 shared task with a system that incorporates spelling error correction techniques. Morante and Busser (2007) participated in the SemEval-2007 competition with a semantic role labeler for Span- ish based on gold standard constituent syntax. These systems use different types of constituent syntax (shallow parsing, full parsing). We are aware of two systems that perform semantic role labeling based on dependency syntax previous to the CoNLL-2008 shared task. Hacioglu (2004) converts the data from the CoNLL-2004 shared task into dependency trees and uses support vector machines. Morante (2008) describes a memory- based semantic role labeling system for Spanish based on gold standard dependency syntax. We developed a memory-based system for the CoNLL-2008 shared task in order to evaluate the …

Content truncated to 500 words