Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2019, Vol. 59 Issue (9): 750-756    DOI: 10.16511/j.cnki.qhdxxb.2019.26.003
  电子工程 本期目录 | 过刊浏览 | 高级检索 |
基于依存树的藏语语义分析
夏吾吉1,2, 华却才让1
1. 青海师范大学 藏文信息处理教育部重点实验室, 西宁 810008;
2. 青海师范大学 民族师范学院, 西宁 810008
Dependency tree based Tibetan semantic dependency analysis
XIA Wuji1,2, HUAQUE Cairang1
1. Tibetan Information Processing Key Laboratory of Ministry of Education, Qinghai Normal University, Xining 810008, China;
2. Normal College for Nationalities, Qinghai Normal University, Xining 810008, China
全文: PDF(1044 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 藏语语义依存分析是以藏语依存句法分析为基础的深层语义研究。该文从词法分析和句法分析等浅层研究出发,结合藏语自身语法结构和语义单位之间的关系特点,实现了藏语语义依存分析。在制定了藏语语义依存关系标注规范并设计了藏语语义依存关系特征模板的前提下,采用感知机进行了藏语语义依存分析模型的训练,经实验该模型在人工标注测试语料上的根准确率、依存弧准确率、依存弧类型准确率及完全准确率等4个指标分别达到了89.56%、78.63%、71.67%及32.32%,证实了该模型在藏语语义依存分析任务中具有良好的性能。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
夏吾吉
华却才让
关键词 藏语语义依存分析标注规范感知机模型    
Abstract:Tibetan semantic dependence analysis is a deep semantic study based on Tibetan-dependent syntactic analysis. This paper starts from the shallow research of lexical analysis and syntactic analysis, and combines the characteristics of Tibetan grammatical structure and semantic unit to realize the semantic dependence analysis of Tibetan for the first time. Under the premise of formulating the Tibetan semantic dependency labeling specification and designing the Tibetan semantic dependency feature template, the perceptual machine is used to train the Tibetan semantic dependence analysis model. The experimental results show that the root accuracy, dependency arc accuracy, dependent arc type accuracy and complete accuracy of the model on manual labeling test corpus reached 89.56%, 78.63%, 71.67% and 32.32%, respectively, which confirmed that the model has good performance in Tibetan semantic dependence analysis tasks.
Key wordsTibetan semantics    dependency analysis    annotation specification    perceptron model
收稿日期: 2018-10-19      出版日期: 2019-08-27
基金资助:青海省科技计划资助项目(2017-GX-146);青海师范大学中青年科研基金资助项目(17ZR11)
通讯作者: 华却才让,副教授,E-mail:peljortsering@qq.com     E-mail: peljortsering@qq.com
引用本文:   
夏吾吉, 华却才让. 基于依存树的藏语语义分析[J]. 清华大学学报(自然科学版), 2019, 59(9): 750-756.
XIA Wuji, HUAQUE Cairang. Dependency tree based Tibetan semantic dependency analysis. Journal of Tsinghua University(Science and Technology), 2019, 59(9): 750-756.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2019.26.003  或          http://jst.tsinghuajournals.com/CN/Y2019/V59/I9/750
  图1 藏语语义依存分析结构
  表1 藏语语义依存关系标注集
  表2 藏语句子类型及语义依存结构特征
  图2 感知机模型
  表3 藏语语义依存分析特征模板
  图3 算法1
  表4 藏语语义依存分析实验结果(%)
[1] 李亚超, 加羊吉, 江静, 等. 融合无监督特征的藏文分词方法研究[J]. 中文信息学报, 2017, 31(2):71-75. LI Y C, JIA Y J, JIANG J, et al. Study on fusion of unsupervised features for Tibetan word segmentation[J]. Journal of Chinese Information Processing, 2017, 31(2):71-75. (in Chinese)
[2] 郑亚楠, 珠杰. 基于词向量的藏文词性标注方法研究[J]. 中文信息学报, 2017, 31(1):112-117. ZHENG Y N, ZHU J. A method of tibetan POS tagging based on distributed representation[J]. Journal of Chinese Information Processing, 2017, 31(1):112-117. (in Chinese)
[3] 华却才让, 赵海兴. 基于判别式的藏语依存句法分析[J]. 计算机工程, 2013, 39(4):300-304. HUA QUE C R, ZHAO H X. Tibetan text dependency syntactic analysis based on discriminant[J]. Computer Engineering, 2013, 39(4):300-304. (in Chinese)
[4] 华却才让, 赵海兴. 藏文复合句的依存句法分析[J]. 中文信息学报, 2016, 30(6):224-229. HUA QUE C R, ZHAO H X. Dependency parsing of tibetan compound sentence[J]. Journal of Chinese Information Processing, 2016, 30(6):224-229. (in Chinese)
[5] 李明琴, 李娟子, 王作英等.中文语义依存关系分析的统计模型[J].计算机学报, 2004, 27(12):1679-1687.LI M Q, LI J X, WANG Z Y, et al. A statistical model for parsing semantic dependency relations in a Chinese sentence[J]. Chinese Journal of Computers, 2004, 27(12):1679-1687. (in Chinese)
[6] 周亮俊, 向阳.基于语句压缩的中文中文语义依存分析[J].计算机应用, 2017, 37(S1):266-269. ZHOU L J, XIANG Y. Chinese semantic dependency parsing based on sentence compression[J]. Journal of Computer Applications, 2017, 37(S1):266-269. (in Chinese)
[7] LI Y M, SH Y Q. Annotating Chinese noun phrases based on semantic dependency graph[J]. International Journal of Asian Language Processing, 2017, 27(1):47-60.
[8] HAO P, THOMSON S, SMITH N A. Deep multitask learning for semantic dependency parsing[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Vancouver, Canada, 2017:2037-2048.
[9] 丁宇. 基于依存图的中文语义分析[D]. 哈尔滨:哈尔滨工业大学, 2014. DING Y. Dependency-graph based Chinese semantic parsing[D]. Harbin:Harbin Institute of Technology, 2014. (in Chinese)
[10] 扎西加, 多拉. 藏语依存树库构建的理论与方法探析[J]. 西藏大学学报(自然科学版), 2015, 30(2):76-83. GYAL T, DUO L. Theory and method of Tibetan dependency treebank construction[J]. Journal of Tibetan University, 2015, 30(2):76-83. (in Chinese)
[11] 祁坤钰. 基于依存关系的藏文语义角色标注研究[J]. 西北民族大学学报(哲学社会科学版), 2014(1):139-143. QI K Y. Research on tibetan semantic role labeling based on dependency[J]. Journal of Northwest University for Nationalities (Philosophy and Social Science), 2014(1):139-143. (in Chinese)
[12] SUN W, CAO J J, WAN X J. Semantic dependency parsing via book embedding[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver, Canada. 2017.
[13] Robinson. Dependency structures and transformation rules[J].Language, 1970.46(2):259-285.
[14] 格桑居冕. 实用藏文文法[M]. 成都:四川民族出版社, 1987. GE S J M. Practical Tibetan grammar[M]. Chengdu:Sichuan National Publishing House, 1987. (in Chinese)
[15] PARK K M, HWANG Y S, RIM H C. Two-phase semantic role labeling based on support vector machines[J]. Proceedings of Conll, 2004:126-129.
[16] 车万翔, 张梅山, 刘挺. 基于主动学习的中文依存句法分析[J]. 中文信息学报, 2012, 26(2):18-22. CHE W X, ZHANG M S, LIU T. Active learning for Chinese dependency parsing[J]. Journal of Chinese Information Processing, 2012, 26(2):18-22. (in Chinese)
[17] MCDONALD R, LERMAN K, PEREIRA F. Multilingual dependency analysis with a two-stage discriminative parser[C]//Proceedings of the Tenth Conference on Computational Natural Language Learning. New York, USA, 2006:216-220.
No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn