“erasmus+ халқаро кредит мобиллик: таълим ва илмий


Download 1.7 Mb.
Pdf ko'rish
bet42/67
Sana17.07.2023
Hajmi1.7 Mb.
#1660800
1   ...   38   39   40   41   42   43   44   45   ...   67
Bog'liq
ICM publication 2018 2

 
5. Conclusions 
In the paper we have discussed the development process of the dictionary of 
Uzbek names and surnames. The dictionary has been developed as a spreadsheet. The 
data included in the dictionary covers the names currently used in Uzbekistan, involving 
also the names resulting from inflection. 
The dictionary has been evaluated by a set of experiments. We have verified 
whether the information contained in the dictionary can be used to identify the names and 
surnames appearing in Uzbek texts. We have also checked whether the dictionary can 
support the task of spell-checking of the texts written in Uzbek, with respect 
to personal names. The experiments have shown that the dictionary can successfully aid 
both tasks.
In the future we plan to perform the experiments on larger sets of texts obtained 
from different sources. We also intend to check whether applying measures of text 
similarity, such as the edit distance, can help to improve the spell-checking process even 
further. 


40 
6. References 
1. Begmatov, E.A., 2016. Uzbek names explained. Tashkent. In Uzbek
2. Bekmurodov, N., 2013. Beautiful Uzbek names. Tashkent. In Uzbek
3. Choudhury, R., K. Kashyap, and N. Deb, 2016. A survey on the different approaches 
of context sensitive spell-checking. International Journal of Engineering Science and 
Computing, 6(6):6872–6873. 
4. Fierman, W., 1992. Language planning and national development: the Uzbek 
experience. Berlin, Germany; New York, USA: Mouton de Gruyter. 
5. Gupta, N. and P. Mathur, 2012. Spell checking techniques in NLP: A survey. 
International Journal of Advanced Research in Computer Science and Software Engineering
2(12):217–221. 
6. Li, X., J. Tracey, S. Grimes, and S. Strassel, 2016. Uzbek-English and Turkish-English 
Morpheme Alignment Corpora. In Proceedings of LREC 2016. pages 2925–2930. 
7. Lawson, E.D., R. Sheil, and V. Mesamed, 1969. Uzbek personal names. In E. Lawson 
and R. Sheil (eds.), The Onomastic Treasure of the CIA. Washington, D.C.: Central Intelligence 
Agency, pages 1–23. 
8. Li, X., J. Tracey, S. Grimes, and S. Strassel, 2016. Uzbek-English and Turkish-English 
Morpheme Alignment Corpora. In Proceedings of LREC 2016. Pages 2925–2930. 
9. Pirinen, T. and K. Linden, 2014. State-of-the-art in weighted finite-state spell-
checking. In CICLing 2014: Computational Linguistics and Intelligent Text Processing, volume 
8404 of LNCS. Berlin, Heidelberg: Springer. 
10. Sayfullaev, A., 2016. Problems of rendering prepositions in translation (on the 
material of English and Uzbek languages). In Scientific enquiry in the contemporary world: 
theoretical basics and innovative approach. pages 91–96. 
11. Singh, S.P., A. Kumar, L. Singh, M. Bhargava, K. Goyal, and B. Sharma, 2016. 
Frequency based spell checking and rule based grammar checking. In Proc. Of International 
Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT). IEEE. 
12. To‘rayev, B. and A. Pakhunov, 2016. erkatoy.uz. 
http://erkatoy.uz/uzb/kutubxona/hikoyalar/. Last access: 24/09/2017. 
13. The Apache Software Foundation, 2017. Apache POI documentation. 
https://poi.apache.org/apidocs/. Last access: 24/09/2017. 

Download 1.7 Mb.

Do'stlaringiz bilan baham:
1   ...   38   39   40   41   42   43   44   45   ...   67




Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©fayllar.org 2024
ma'muriyatiga murojaat qiling