Abstract
In this study, we made some heuristic rules related to the boundary of protein names for automated extraction of protein names from biomedical literatures. The automated extraction of protein names was carried out based on Support Vector Machine (SVM). From the analysis of the results, we found whether some words of modifier words set were included or not as part of protein names. It is critical whether the modifier words set is or not included in a protein name. Adapting some heuristic rules to the corpus, the F-score was improved about 1.3% (from 76.10% to 77.41%) compared with the case without adapting proposed rules.
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
Yamamoto, K., Kudo, T., Konagaya, A., Matsumoto, Y.: Proceedings of the ACL 2003 Workshop on NLP in Biomedicine, pp. 65–72 (2003)
Franzén, K., Eriksson, G., Olsson, F., Asker, L., Lidén, P., Cöster, J.: International Journal of Medical Informatics 67, 49–61 (2002)
Takeuchi, K., Collier, N.: Proceedings of the ACL 2003 Workshop on NLP in Biomedicine, pp. 57–64 (2003)
Fukuda, K., Tamura, A., Tsunoda, T., Takagi, T.: Proceedings of the Pacific Symposium on Biocomputing, pp. 705–716 (1999)
Kudo, T., Matsumoto, Y.: North American Chapter of the Association for Computational Linguistics (NAACL), pp. 192–199 (2001)
Ohta, T., Tateisi, Y., Mima, H., Tsujii, J.: Proceedings of he Human Language Technology Conference, HLT 2002 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mitsumori, T., Fation, S., Murata, M., Doi, K., Doi, H. (2004). Boundary Correction of Protein Names Adapting Heuristic Rules. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2004. Lecture Notes in Computer Science, vol 2945. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24630-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-24630-5_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21006-1
Online ISBN: 978-3-540-24630-5
eBook Packages: Springer Book Archive