Abstract
Traditional Mongolian Unicode Encoding has serious problems as several pairs of vowels with the same glyphs but different pronunciations are coded differently. We expose the severity of the problem by examples from our Mongolian corpus and propose two ways to alleviate the problem: first, developing a publicly available Mongolian input method that can help users to choose the correct encoding and second, a normalization method to solve the data sparseness problems caused by the proliferation of homographs. Experiments in search engines and statistical machine translation show that our methods are effective.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The authors can scarcely find a Unicoded traditional Mongolian web site in the year 2014, although things began to change starting from the year 2015.
- 2.
. - 3.
. - 4.
To emphasize the letter ang is one code point, we transliterate it as n̅g̅. It is often pronounced as [ŋ].
- 5.
- 6.
Prof. Garudi of Inner Mongolia Normal University, personal communication.
- 7.
Personal communication.
- 8.
- 9.
- 10.
The letters o and u are regarded equivalent letters. We collected 22 such equivalent pairs and they form the letter equivalence table. Note that equivalent letters do not always have same glyphs in all positions, e.g. some letters are only equivalent at the medial positions.
- 11.
We rely on the Microsoft Uniscribe engine to generate the correct glyphs. However, as [1] points out, even if Microsoft failed to generate some of the correct glyphs.
- 12.
- 13.
Google’s powerful engine can index pdf files, while ours does not yet.
- 14.
For this experiment, we only indexed two popular Mongolian website: www.mgyxw.net and mgl.nmg.gov.cn.
- 15.
References
Batjargal, B., Khaltarkhuu, G., Kimura, F., Maeda, A.: A study of traditional Mongolian script encodings and rendering: use of unicode in OpenType fonts. Int. J. Asian Lang. Proc. 21(1), 23–44 (2011)
Chinggaltai: A Grammar of the Mongol Language. Frederick Ungar Publishing Co, New York (1963)
Choijinzhab: Mongolian Encoding. Inner Mongolia University Press, Hohhot. (确精扎布: 蒙古文编码. 内蒙古大学出版社, 呼和浩特) (2000). (in Chinese) http://www.babelstone.co.uk/Mongolian/MGWBM.html
Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. Int. J. Pattern Recogn. Artif. Intell. 18(03), 265–298 (2004)
Daoerji, F., Fengshan, B., Huijuan, W.U.: Research on Mongolian input method in unicode. J. Chin. Inf. Process. 24(6), 120–124+128 (2010). (in Chinese)
Goldsmith, J.: Vowel harmony in Khalkha Mongolian, Yaka, Finnish and Hungarian. Phonology 2(01), 253–275 (1985)
MünggeGal: Menksoft Mongolian IME. http://www.menksoft.com/
Ochir, Wang, G.F.: Corpus and Mongolian inputting methods. In: International Conference on Chinese Computing 2005, Singapore (2005)
Papineni, K., Roukos, S., Ward, T., Zhu, W. J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of 40th Annual Meeting on Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002)
Poppe, N.: Grammar of Written Mongolian. Otto Harrassowitz Verlag, Wiesbaden (1974)
The Unicode Consortium: The Unicode Standard, Version 8.0.0 (2015). http://www.unicode.org/versions/Unicode8.0.0/
Acknowledgements
The work done in this paper is partially supported by the Research Fund for the Doctoral Program of Higher Education of China (No. 20130121110040), National High-Tech R&D Program of China (No. 2012BAH14F03), and the Special Fund Project of Ministry of Education of China (Intelligent Conversion System from Simplified to Traditional Chinese Characters). We thank Dr. Yanlong He for kindly providing the Mongolian-Chinese test corpus for the statistical machine translation experiment.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Wang, B., Shi, X., Chen, Y. (2016). Coping with Problems of Unicoded Traditional Mongolian. In: Sun, M., Huang, X., Lin, H., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. NLP-NABD CCL 2016 2016. Lecture Notes in Computer Science(), vol 10035. Springer, Cham. https://doi.org/10.1007/978-3-319-47674-2_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-47674-2_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-47673-5
Online ISBN: 978-3-319-47674-2
eBook Packages: Computer ScienceComputer Science (R0)