微信服务号

微信订阅号

2025年6月1日 19:42 星期日
首页 > 过刊浏览>2015年第26卷第12期 >3151-3161. DOI:10.13328/j.cnki.jos.004816
PDF HTML阅读 XML下载 导出引用 引用提醒
基于树形条件随机场的跨语言时态标注
作者:
基金项目:

国家自然科学基金(61075058);国家科技支撑计划(2012BAH14F03)


Cross-Lingual Tense Tagging Based on Tree Conditional Random Fields
Author:
Fund Project:

National Natural Science Foundation of China (61075058); National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2012BAH14F03)

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [27]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    提出时态树的概念和构造方法,从而将汉英时态转换问题转换为时态树标注的问题.而后,使用树形条件随机场为未标注时态树的结点标注英语时态.提出的特征函数的模板较好地满足了模型推断的需要.实验结果表明:与基于线性条件随机场模型的时态标注方法相比,基于时态树方法的准确率有大幅度的提高,说明使用时态树能够更好地表达子句间时态的依赖关系.

    Abstract:

    In this paper, the concept of a tense tree and its construction method are proposed such that the issue of Chinese-English tense conversion is transformed into the issue of tagging a tense tree. Futher, tree-CRF is used to tag nodes of the untagged tense tree with English tenses. Templates of feature functions are suitable for the need of model inference. Experimental results show that the method of tree-based tense tagging is much better than linear-based tense tagging, and that tense trees can better express tense dependencies between clauses.

    参考文献
    [1] Liu Q, Yu SW. Discussion on the difficulties of Chinese-English machine translation. In:Huang CL, ed. Proc. of the Int'l Conf. on Chinese Information Processing. Beijing:Tsinghua University Press, 1998. 507-514(in Chinese).
    [2] Gong Z, Zhang M, Tan C, Zhou G. N-Gram-Based tense models for statistical machine translation. In:Proc. of the EMNLP. East Stroudsburg:Association for Computational Linguistics(ACL), 2012. 276-285.
    [3] Gong QY. Chinese Phase, Tense and Aspect. Beijing:China Commerce and Trade Press, 1995. 1-95(in Chinese).
    [4] Cheng JH, Dai XY, Chen JJ, Wang QX. Processing of tense and aspect in Chinese-English machine translation. Application Research of Computers, 2004,21(3):79-81(in Chinese with English abstract).
    [5] Ma HM, Wang T, Chen HW. Time phrase parsing of Chinese text and tense calculus. Journal of Computer Research and Development, 2002,39(10):1211-1220(in Chinese with English abstract).
    [6] Ma HM. Research on the representation and application of Chinese context in Chinese-English machine translation[Ph.D. Thesis]. Changsha:National University of Defense Technology, 2002(in Chinese with English abstract).
    [7] Ye Y, Zhang Z. Tense tagging for verbs in cross-lingual context:A case study. In:Proc. of the IJCNLP. Berlin, Heidelberg:Springer-Verlag, 2005. 885-895.[doi:10.1007/11562214_77]
    [8] Murata M, Uchimoto K, Ma Q, Isahara H. Using a support-vector machine for Japanese-to-English translation of tense, aspect, and modality. In:Proc. of the ACL Workshop on the Data-Driven Machine Translation. East Stroudsburg:Association for Computational Linguistics(ACL), 2001. 1-8.[doi:10.3115/1118037.1118052]
    [9] Murata M, Ma Q, Uchimoto K, Kanamaru T, Isahara H. Japanese-to-English translations of tense, aspect, and modality using machine-learning methods and comparison with machine-translation systems on market. Language Resources and Evaluation, 2006, 40(3):233-242.[doi:10.1007/s10579-007-9022-z]
    [10] Gong ZX, Zhang M, Tan CL, Zhou GD. Classifier-Based tense model for SMT. In:Proc. of the 24th Int'l Conf. on Computational Linguistics. 2012. 411-420.
    [11] Chen YJ. Research on several key issues of Chinese-English machine translation[Ph.D. Thesis]. Xiamen:Xiamen University, 2011(in Chinese with English abstract).
    [12] Ye Y, Fossum V, Abney S. Latent features in automatic tense translation between Chinese and English. In:Hwee Tou Ng, ed. Proc. of the 5th SIGHAN Workshop on Chinese Language Processing. Australia:BPA Digital Press, 2006. 48-55.
    [13] Olson M, Traum D, Dykema C, Weinberg A. Implicit cues for explicit generation:Using telicity as a cue for tense structure in a Chinese to English MT system. In:Proc. of the Machine Translation Summit VⅡI-Machine Translation in the Information Age. 2001. 259-264.
    [14] Lu JM, Ma Z. Comments on Function Word of Modern Chinese. Beijing:Peking University Press, 1999. 106-141(in Chinese).
    [15] Lafferty J, McCallum A, Pereira F. Conditional random fields:Probabilistic models for segmenting and labeling sequence data. In:Proc. of the 18th Int'l Conf. on Machine Learning. 2001. 282-289.
    [16] Tang J, Hong MC, Li JZ, Liang B. Tree-Structured conditional random fields for semantic annotation. In:Cruz I, ed. Proc. of the 5th Int'l Conf. of Semantic Web. Berlin, Heidelberg:Springer-Verlag, 2006. 640-653.[doi:10.1007/11926078_46]
    [17] Cohn T, Blunsom P. Semantic role labeling with tree conditional random fields. In:Proc. of the 9th Conf. on Computational Natural Language Learning. East Stroudsburg:Association for Computational Linguistics(ACL), 2005. 169-172.
    [18] Jousse F, Gilleron R, Tellier I, Tommasi M. Conditional random fields for XML trees. In:Proc. of the ECML Workshop on Mining and Learning in Graphs. 2006. 525-533.
    [19] Moreau E, Tellier I. The crotal SRL system:A generic tool based on tree-structured CRF. In:Proc. of the 19th Conf. on Computational Natural Language Learning. 2009. 91-96.
    附中文参考文献:
    [1] 刘群,俞士汶.汉英机器翻译的难点分析.见:中文信息处理国际会议论文集.北京:清华大学出版社,1998.507-514.
    [3] 龚千炎.汉语的时相时制时态.北京:商务印书馆,1995.1-95.
    [4] 程节华,戴新宇,陈家骏,王启祥.汉英机器翻译中时体态处理.计算机应用研究,2004,21(3):79-81.
    [5] 马红妹,王挺,陈火旺.汉语篇章时间短语的分析与时制验算.计算机研究与发展,2002,39(10):1211-1220.
    [6] 马红妹.汉英机器翻译中汉语上下文语境的表示与应用研究[博士学位论文].长沙:国防科学技术大学,2002.
    [11] 陈怡疆.汉英机器翻译若干关键问题的研究[博士学位论文].厦门:厦门大学,2011.
    [14] 陆俭明,马真.现代汉语虚词散论.北京:北京大学出版社,1985.106-141.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

陈怡疆,徐海波,史晓东,苏畅.基于树形条件随机场的跨语言时态标注.软件学报,2015,26(12):3151-3161

复制
分享
文章指标
  • 点击次数:2845
  • 下载次数: 4896
  • HTML阅读次数: 1332
  • 引用次数: 0
历史
  • 收稿日期:2014-03-23
  • 最后修改日期:2014-08-27
  • 在线发布日期: 2015-12-04
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会CCF数字图书馆Int'l J of Softw Info计算机系统应用
您是第19987540位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京市海淀区中关村南四街4号,邮政编码：100190
电话：010-62562563 传真：010-62562533 Email：jos@iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号