Abstract
A boosting-based ensemble learning can be used to improve classification accuracy by using multiple classification models constructing to cope with errors obtained from preceding steps. This paper presents an application of the boosting-based ensemble learning with penalty setting profiles on automatic unknown word recognition in Thai. Treating a sequential task as a non-sequential problem requires us to rank a set of generated candidates for a potential unknown word position. Since the correct candidate might not located at the highest rank among those candidates in the set, the proposed method provides penalties, in the form of a penalty setting profile, to improper ranking in order to reconstruct the succeeding classification model. In addition a number of alternative penalty setting profiles are introduced and their performances are compared on the task of extracting unknown words from a large Thai medical text. Using the naïve Bayes as the base classifier for ensemble learning, the proposed method achieves the accuracy of 89.24%, which is an improvement of 9.91%, 7.54%, 5.25% over conventional naïve Bayes, non-ensemble version, and flat penalty setting profile.
This work was partially funded by NECTEC of Thailand via research grant for Automatic Tagger for Named Entity in Thai News Corpus Project (NT-B-22-KE-38-52-01).
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
Charoenpornsawat, P.: et al.: Feature-based thai unknown word boundary identification using winnow. In: Proc. of APCCAS 1998, Chiang Mai, Thailand, pp. 547–550 (November 1998)
Dietterich, T.G.: Ensemble methods in machine learning. In: Kittle, J., Roli, F. (eds.) Multiple Classifiers Systems, pp. 1–15. Springer, Heidelberg (2000)
Freund, Y., Schapire, R.E.: A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence 14(5), 771–780 (1999)
Haruechaiyasak, C., et al.: A collaborative framework for collecting thai unknown words from the web. In: Proc. of the COLING/ACL-2006, Sydney, Australia, pp. 345–352 (July 2006)
Kawtrakul, A., et al.: Automatic thai unknown word recognition. In: Proc. of NLPRS 1997, Phuket, Thailand, pp. 341–346 (October 1997)
Sornlertlamvanich, V., Tanaka, H.: The automatic extraction of open compounds from text. In: Proc. of COLING 1996, Copenhagen, Denmark, pp. 1143–1146 ( August 1996)
TeCho, J., et al.: A corpus-based approach for automatic thai unknown word recognition using boosting techniques. IEICE Transactions on Information and Systems E92-D(12), 2321–2333 (2009)
Theeramunkong, T., et al.: Pattern-based features vs. statistical-based features in decision trees for word segmentation. IEICE Transactions on Information and Systems E87-D(5), 1254–1260 (2004)
Theeramunkong, T., et al.: A framework for constructing a thai medical knowledge base. In: Proc. of KICSS 2007, JAIST, Ishikawa, Japan, pp. 45–50 (November 2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
TeCho, J., Nattee, C., Theeramunkong, T. (2010). Boosting-Based Ensemble Learning with Penalty Setting Profiles for Automatic Thai Unknown Word Recognition. In: Pan, JS., Chen, SM., Nguyen, N.T. (eds) Computational Collective Intelligence. Technologies and Applications. ICCCI 2010. Lecture Notes in Computer Science(), vol 6422. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16732-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-16732-4_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16731-7
Online ISBN: 978-3-642-16732-4
eBook Packages: Computer ScienceComputer Science (R0)