维吾尔语和韩语形态分析之模型构建

doi:10.13190/j.jbupt.2017-117

北京邮电大学学报 ›› 2018, Vol. 41 ›› Issue (1): 88-94.doi: 10.13190/j.jbupt.2017-117

维吾尔语和韩语形态分析之模型构建

徐春^1,2,3,4, 蒋同海^1,3, 于凯⁴, 姜文斌^2,5

1. 中国科学院新疆理化技术研究所, 乌鲁木齐 830011;
2. 中国科学院大学, 北京 100049;
3. 新疆民族语音语言信息处理重点实验室, 乌鲁木齐 830011;
4. 新疆财经大学计算机科学与工程学院, 乌鲁木齐 830012;
5. 中国科学院计算技术研究所智能信息重点实验室, 北京 100190

发布日期:2018-01-04
作者简介:徐春(1977-),女,博士生,E-mail:xuchun@mails.ucas.ac.cn;蒋同海(1963-),男,研究员,博士生导师.
基金资助:
新疆自治区高校科研计划面上项目（XJEDU2017M027）；新疆自治区自然科学基金项目（2015211B034）；新疆自治区重点实验室开放课题（2015KL031）；新疆自治区重大科技专项课题（2016A03007-3）；国家自然科学基金项目（71561025）；新疆自治区高校科研计划重点项目（XJEDU2016I038）；新疆维吾尔自治区自然科学基金面上项目（2016D01A060）

Model Construction of Uygur and Korean Morphological Analysis

XU Chun^1,2,3,4, JIANG Tong-hai^1,3, YU Kai⁴, JIANG Wen-bin^2,5

1. Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi 830011, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China;
3. Xinjiang Key Laboratory of Minority Speech and Language Information Processing, Urumqi 830011, China;
4. College of Computer Science and Engineering, Xinjiang University of Finance and Economics, Urumqi 830012, China;
5. Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Science, Beijing 100190, China

Published:2018-01-04

摘要/Abstract

摘要： 为维吾尔语和韩语形态分析建立了一种图状结构的判别式模型，该模型将语句的形态分析建模为形态成分的图状结构，通过灵活丰富的特征设计描述了词语内部形态成分之间以及分属相邻词语的形态成分之间的关联约束.相比传统的线性模型，图状模型更好地考虑了各形态成分之间的语言学关联，从而取得更高的整句分析性能.在维吾尔语和韩语上的实验结果表明，图状模型相比线性模型的性能有一定提升，形态分析词级准确率分别提升了4.4%和2.8%.

关键词: 形态分析, 黏着语, 图状模型, 线性模型

Abstract: A discriminant model of the graphic structure is established for the morphological analysis of Uighur and Korean language. The model builds the morphological analysis of the sentence into the graphic structure of morphological components, and describes the correlation between the morphological components of the words inside and the morphological components of the adjacent words through flexible and rich feature design. Compared with the traditional linear model, the pattern model is better to consider the linguistic association between the morphological components, and it is expected to achieve higher sentence analysis performance. The experimental results in Uighur and Korean indicate that the graphic model achieves certain performance improvement comparing with the linear model, and the word level accuracy of morphological analysis respectively increases by 4.4 and 2.8 percentage points.

Key words: morphological analysis, agglutinative language, graphic model, linear mode

中图分类号:

TN391.1

徐春, 蒋同海, 于凯, 姜文斌. 维吾尔语和韩语形态分析之模型构建[J]. 北京邮电大学学报, 2018, 41(1): 88-94.

XU Chun, JIANG Tong-hai, YU Kai, JIANG Wen-bin. Model Construction of Uygur and Korean Morphological Analysis[J]. Journal of Beijing University of Posts and Telecommunications, 2018, 41(1): 88-94.

参考文献

[1] 赛迪亚古丽·艾尼瓦尔, 向露, 宗成庆, 等. 基于多策略的维吾尔语词干提取方法[J]. 中文信息学报, 2015, 29(5):204-210. Sediyegvl Enwer, Xiang Lu, Zong Chengqing, et al. A multi-strategy approach to uyghur stemming[J]. Journal of Chinese Information Processing, 2015, 29(5):204-210.
[2] 徐春, 杨勇, 蒋同海. 基于机器翻译的维吾尔语形态分析研究[J]. 计算机工程与应用, 2017, 53(14):138-142. Xu Chun, Yang Yong, Jiang Tonghai. Research on machine translation based uyghur morphological analysis[J]. Computer Engineering and Applications, 2017, 53(14):138-142.
[3] 麦热哈巴·艾力, 姜文斌, 王志洋, 等. 维吾尔语词法分析的有向图模型[J]. 软件学报, 2012, 23(12):3115-3129. Mairehaba·AILI. Jiang Wenbin, Wang Zhiyang. Directed graph model of uyghur morphological analysis[J]. Journal of Software, 2012, 23(12):3115-3129.
[4] 张海波, 蔡洽吾, 姜文斌, 等. 基于联合音变还原和形态切分的形态分析方法[J]. 中文信息学报, 2014, 28(6):10-16. Zhang Haibo, Cai Qiawu, Jiang Wenbin. Morphological segmentation model for morphological analysis[J]. Journal of Chinese Information Processing, 2014, 28(6):10-16.
[5] Lee D G, Rim H C. Probabilistic modeling of korean morphology[J]//IEEE Transactions on Audio, Speech, and Language Processing, 2009, 17(5):945-955.
[6] Ablimit M, Kawahara T, Pattar A, et al. Stem-affix based Uyghur morphological analyzer[J]. International Journal of Future Generation Communication and Networking, 2008, 9(2):59-72.
[7] Ruokolainen T, Kohonen O, Virpioja S et al. Supervised morphological segmentation in a low-resource learning setting using conditional random fields[C]//Proceeding of the Seventeenth Conference on Computational National Language Learning. Sofia:Association for Computational Linguistics, 2013:8-9.
[8] 赵伟, 侯宏旭, 丛伟, 等. 基于条件随机场的蒙古语词切分研究[J]. 中文信息学报, 2010, 24(5):31-35. Zhao Wei, Hou Hongxu, Cong Wei. Research on conditional random fields based mongolian word segmentation[J]. Journal of Chinese Information Processing, 2010, 24(5):31-35.
[9] Jiang W, Mi H, Liu Q. Word lattice reranking for Chinese word segmentation and part-of-speech tagging[C]//Proceedings of the 22^nd International Conference on Computational Linguistics. Manchester:[s.n.], 2008:385-392.
[10] 华却才让. 基于树到串藏语机器翻译若干关键技术研究[D]. 西安:陕西师范大学, 2014.
[11] Michael C. Discriminative training methods for hidden markov models:theory and experiments with perceptron algorithms[C]//Proceedings of EMNLP, 2002, Pennsylvania, USA, 410(21-23):1-8.
[12] Le Zhang. Maximum entropy modeling toolkit for python and C++[EB/OL]. (2011-09-09)[2017-05-06]. http://homepages.inf.ed.ac.uk/lzhang10/maxent_toolkit.html

维吾尔语和韩语形态分析之模型构建

Model Construction of Uygur and Korean Morphological Analysis

RichHTML

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	赵霞, 倪颖婷, 李瞻宁. 基于RLS的改进双线性模型的稳定性分析[J]. 北京邮电大学学报, 2018, 41(1): 121-124.
[2]	肖丁, 贾亚璞, 石川. 云计算环境下的非线性能耗建模方法[J]. 北京邮电大学学报, 2016, 39(1): 107-111.
[3]	郭岗，牛文生. 模糊双线性关联系统的反馈控制[J]. 北京邮电大学学报, 2011, 34(1): 135-149.