Research on Automatic Tagging of Parts of Speech for Tibetan Texts Based on the Condition of Random Fields

Article Preview

Abstract:

It’s a basic work for Tibetan information processing to tag the Tibetan parts of speech,the results can be used in machine translation, speech synthesis and so on. By studying the Tibetan language grammar and the classification of Tibetan parts of speech, established the Tibetan parts of speech tagging sets, and tagged the corpus, used the CRFs to solve the problem that automatic tagging of Tibetan parts of speech, the experimental results show that in the closed test set, part-of-speech tagging accuracy is 94.2%, and in the opening set, the accuracy is 91.5%.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

784-787

Citation:

Online since:

February 2014

Export:

Price:

* - Corresponding Author

[1] Su Junfeng, Qi kunyu. Researchs of Part of Speech Tagging for Tibetan Texts Based on Hidden Markov Model [J],Journal of northwest university for nationalities,2009(01): 42-45.

Google Scholar

[2] zhaoqi Bian.  Pattern recognition [M] . Beijing:Tsinghua University Press, (2000).

Google Scholar

[3] Shanmudan. New Tibetan dictionary[M] . Xining:Qinghai minorities press, (1979).

Google Scholar

[4] Pereira L J, Mccallum F A. Conditional random fields: probabilistic models for segmenting and labeling sequence data [C] / / Proc. of 18th ICML. San Fr ancisco, USA: AAAI Press, 2001: 282- 289.

DOI: 10.1145/1015330.1015422

Google Scholar

[5] Huang Yi-Chin, Wu Chung-Heng, Chao Yu-Ting. Personalized Spectral and Prosody Conversion Using Frame-Based Codeword Distribution and Adaptive CRF [J]. IEEE Transactions On Audio Speech And Language Processing  , 2012:49-60.

DOI: 10.1109/tasl.2012.2213247

Google Scholar

[6] Ni Chong-Jia, Zhang Ai-Ying, Liu Wen-Ju. Automatic Prosodic Break Detection And Feature Analysis[J]. Journal Of Computer Science And Technology , 2012:1184-1196.

DOI: 10.1007/s11390-012-1295-z

Google Scholar

[7] J. Lafferty, A. McCallum and F. Pereira. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data[C]. In Proceedings of ICML-2001:282-289.

DOI: 10.1145/1015330.1015422

Google Scholar

[8] Roman Klinger, Katrin Tomanek. Classical Probabilistic Models and Conditional Random Fields. Algorithm Engineering Report, (2007).

Google Scholar

[9] Jingchen Liu, Huang Minlie, Xiaoyan Zhu. Recognizing Biomedical Named Entities Using Skip-chain Condition Random Fields [C] / / Proceedings of the 2010 Workshop on Biomedical Natural Language Processing. PA: Association for Computational Linguistics, 2010: 10- 18.

Google Scholar

[10] Peng Lu, Yiping Yang, Yibo Gao. Hierarchical Conditional Random Fields(HCRF) for Chinese named entity tagging [C] / / The 3rd International Conference on Natural Computation. Washington: IEEE Computer Society , 2007: 24- 28.

DOI: 10.1109/icnc.2007.415

Google Scholar

[11] Wen-bo HU, Yun-cheng DU, Xue-qiang LV, et al. Study on Chinese named entity recognitionbased on cascaded Conditional Random Fields. Computer Engineering and Applications,2009,45(1): 163-165.

Google Scholar