Abstract
This chapter presents the application of the ETL approach to semantic role labeling (SRL). The SRL task consists in detecting basic event structures in a given text. Some of these event structures include who did what to whom, when and where. We evaluate the performance of ETL over two English language corpora: CoNLL-2004 and CoNLL-2005. ETL system achieves regular results for the two corpora. However, for the CoNLL-2004 Corpus, our ETL system outperforms the TBL system proposed by Higgins [4]. ETL committee significantly improves the ETL results for the two corpora. This chapter is organized as follows. In Sect. 8.1, we describe the selected corpora. In Sect. 8.2, we detail some modeling configurations used in our SRL system. In Sect. 8.3, we show some configurations used in the machine learning algorithms. Section 8.4 presents the application of ETL for the CoNLL-2004 Corpus. Section 8.5 presents the application of ETL for the CoNLL-2005 Corpus. Finally, Sect. 8.6 presents some concluding remarks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Carreras, X., Màrquez, L.: Introduction to the conll-2004 shared task: semantic role labeling. In: Ng, H.T., Riloff, E. (eds.) Proceedings of the Conference on Computational Natural Language Learning, pp. 89–97. Association for Computational Linguistics, Boston, Massachusetts, USA (2004)
Carreras, X., Màrquez, L.: Introduction to the conll-2005 shared task: semantic role labeling. In: Proceedings of the Conference on Computational Natural Language Learning, pp. 152–164. Association for Computational Linguistics, Ann Arbor, MI, USA (2005)
Hacioglu, K., Pradhan, S.S., Ward, W.H., Martin, J.H., Jurafsky, D.: Semantic role labeling by tagging syntactic chunks. In: Ng, H.T., Riloff, E. (eds.) HLT-NAACL 2004 Workshop: Eighth Conference on Computational Natural Language Learning (CoNLL-2004). Association for Computational Linguistics, Boston, Massachusetts, USA (2004)
Higgins, D.: A transformation-based approach to argument labeling. In: Ng, H.T., Riloff, E. (eds.) HLT-NAACL 2004 Workshop: Eighth Conference on Computational Natural Language Learning (CoNLL-2004), pp. 114–117. Association for Computational Linguistics, Boston, Massachusetts, USA (2004)
Marcus, M.P., Marcinkiewicz, M.A., Santorini, B.: Building a large annotated corpus of english: the penn treebank. Comput. Linguist. 19(2), 313–330 (1993)
Màrquez, L., Comas, P.R., Giménez, J., Català, N.: Semantic role labeling as sequential tagging. In: Proceedings of the Ninth Conference on Computational Natural, Language Learning (CONLL’05), pp. 193–196 (2005)
Palmer, M., Gildea, D., Kingsbury, P.: The proposition bank: an annotated corpus of semantic roles. Comput. Linguist. 31(1), 71–106 (2005). doi:10.1162/0891201053630264
Punyakanok, V., Roth, D., tau Yih, W.: The necessity of syntactic parsing for semantic role labeling. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 1117–1123 (2005)
Surdeanu, M., Màrquez, L., Carreras, X., Comas, P.: Combination strategies for semantic role labeling. J Artif. Intell. Res. 29, 105–151 (2007)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2012 The Author(s)
About this chapter
Cite this chapter
dos Santos, C.N., Milidiú, R.L. (2012). Semantic Role Labeling. In: Entropy Guided Transformation Learning: Algorithms and Applications. SpringerBriefs in Computer Science. Springer, London. https://doi.org/10.1007/978-1-4471-2978-3_8
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2978-3_8
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-2977-6
Online ISBN: 978-1-4471-2978-3
eBook Packages: Computer ScienceComputer Science (R0)