留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

统一框架的混合依存句法分析

吴福祥 周付根

吴福祥, 周付根. 统一框架的混合依存句法分析[J]. 电子科技大学学报, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017
引用本文: 吴福祥, 周付根. 统一框架的混合依存句法分析[J]. 电子科技大学学报, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017
WU Fu-xiang, ZHOU Fu-gen. Unified Framework for Hybrid Dependency Parsin[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017
Citation: WU Fu-xiang, ZHOU Fu-gen. Unified Framework for Hybrid Dependency Parsin[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017

统一框架的混合依存句法分析

doi: 10.3969/j.issn.1001-0548.2016.01.017
详细信息
  • 中图分类号: TN912

Unified Framework for Hybrid Dependency Parsin

  • 摘要: 监督统计句法分析器的性能很大程度依赖于昂贵而有限的人工标注数据。为充分利用现有标注树库而不需额外设计句法分析器,该文提出了一种混合句法处理管线。该管线以基于最大生成树算法和线性链式条件随机场的句法分析器为基本框架,融合使用不同树库进行混合训练,综合利用不同树库对应的基线分析器解析的依存骨架,提取交叉信息,并在基本框架上构建了综合句法分析器。实验结果表明,该方法可以有效地提升单一树库的句法分析器的分析精度。
  • [1] ZHOU Guang-you, CAI Li, ZHAO Jun, et al. Phrase-based translation model for question retrieval in community question answer archives[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2011: 653-662.
    [2] 宗成庆. 统计自然语言处理[M]. 北京: 清华大学出版社, 2008. ZONG Cheng-qing. Statistical natural language processing[M]. Beijing: Tsinghua University press, 2008.
    [3] NIVRE J, HALL J, NILSSON J. Memory-based dependency parsing[C]//Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL). Boston, USA: Association for Computational Linguistics, 2004: 49-56.
    [4] NIVRE J, HALL J, NILSSON J. MaltParser: a data-driven parser-generator for dependency parsing[C]//Proceedings of the 15th International Conference on Language Resources and Evaluation (LREC2006). Genoa, Italy: European Language Resources Association, 2006: 2216-2219.
    [5] CHE Wan-xiang, SPITKOVSKY V L, LIU Ting. A comparison of Chinese parsers for stanford dependencies[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012). Jeju Island, Korea: Association for Computational linguistics, 2012: 11-16.
    [6] LIU Ting, MA Jin-shan, LI Sheng. Building a dependency treebank for improving Chinese parser[J]. Journal of Chinese Languages and Computing, 2006, 16(4): 207-224.
    [7] XUE Nai-wen, XIA Fei, CHIOU Fu-dong, et al. The penn Chinese treebank: Phrase structure annotation of a large corpus[J]. Natural Language Engineering, 2005, 10(4): 1-30.
    [8] MCDONALD R, CRAMMER K, PEREIRA F. Online large-margin training of dependency parsers[C]//Proceeding of the 43th Annual Meeting of the Association for Computational Linguistics. Ann Arbor, USA: Association for Computational Linguistics, 2005: 91-98.
    [9] SHA F, PEREIRA F. Shallow parsing with conditional random fields[C]//Proceedings of the 2003 Human Language Technology Conference and North American Chapter of the Association for Computational Linguistics (HLT/NAACL-03). Edmonton, Canada: Association for Computational Linguistics, 2003: 134-141.
    [10] NIVRE J, MCDONALD R. Integrating graph-based and transition-based dependency parsers[C]//Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Columbus, USA: Association for Computational Linguistics, 2008: 950-958.
    [11] ZHANG Yue, CLARK S. A tale of two parsers: Investigating and combining graph-based and transitionbased dependency parsing using beam-search[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP '08). Stroudsburg, USA: Association for Computational Linguistics, 2008: 562-571.
    [12] CARRERAS X. Experiments with a higher-order projective dependency parser[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing. Prague, The Czech Republic: Association for Computational Linguistics, 2007: 957-961.
    [13] GREEN N. Hybrid combination of constituency and dependency trees into an ensemble dependency parser[C]//Proceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data. Avignon, France: Association for Computational Linguistics, 2012: 19-26.
    [14] LI Zheng-hua, LIU Ting, CHE Wan-xiang. Exploiting multiple treebanks for parsing with Quasi-synchronous grammars[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. Jeju Island, Korea: Association for Computational Linguistics, 2012: 675-684.
    [15] NIU Zheng-yu, WANG Hai-feng, WU Hua. Exploiting heterogeneous treebanks for parsing[C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Suntec, France: Association for Computational Linguistics, 2009: 46-54.
    [16] ZHOU Guang-you, ZHAO Jun. Joint inference for heterogeneous dependency parsing[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Sofia, The Republic of Bulgaria: Association for Computational Linguistics, 2013: 104-109.
  • [1] 林小蝶, 魏朝晖.  经典、量子及其混合场景下的经典关联生成协议 . 电子科技大学学报, 2023, 52(1): 2-7. doi: 10.12178/1001-0548.2022187
    [2] 赵娜, 柴焰明, 尹春林, 杨政, 王剑, 苏适.  基于最大连通子图相对效能的相依网络鲁棒性分析 . 电子科技大学学报, 2021, 50(4): 627-633. doi: 10.12178/1001-0548.2020440
    [3] 李响, 严毅, 刘明辉, 刘明.  基于多条件对抗和梯度优化的生成对抗网络 . 电子科技大学学报, 2021, 50(5): 754-760. doi: 10.12178/1001-0548.2020415
    [4] 鲁远耀, 周腾鹤, 闫捷.  基于局部马尔科夫随机场的模型校准嘴唇分割方法 . 电子科技大学学报, 2018, 47(3): 430-435. doi: 10.3969/j.issn.1001-0548.2018.03.017
    [5] 王智文, 蒋联源, 王宇航, 欧阳浩, 张灿龙, 黄镇谨, 王鹏涛.  基于动作子空间和权重条件随机场的行为识别王智文 . 电子科技大学学报, 2017, 46(2): 412-418. doi: 10.3969/j.issn.1001-0548.2017.02.016
    [6] 杨挺, 杨青, 唐勇.  WSN的移动Agent随机模式与分析 . 电子科技大学学报, 2015, 44(3): 439-444. doi: 10.3969/j.issn.1001-0548.2015.03.021
    [7] 何晓霜, 瞿孟虹, 游凌.  同频混合信号参数联合最大似然递归估计 . 电子科技大学学报, 2015, 44(3): 339-343. doi: 10.3969/j.issn.1001-0548.2015.03.004
    [8] 刘伟, 胡志刚, 刘宏韬.  基于抽象语法树和多态机制的复杂条件语句自动重构研究 . 电子科技大学学报, 2014, 43(5): 736-741. doi: 10.3969/j.issn.1001-0548.2014.05.018
    [9] 张磊, 李珊, 彭舰, 陈黎, 黎红友.  基于依存关系和最大熵的特征-情感对分类 . 电子科技大学学报, 2014, 43(3): 420-425. doi: 10.3969/j.issn.1001-0548.2014.03.018
    [10] 李国颖, 成柏松, 张鹏, 李大庆.  相互依存网络鲁棒性研究综述 . 电子科技大学学报, 2013, 42(1): 23-28. doi: 10.3969/j.issn.1001-0548.2013.01.006
    [11] 张和发, 李立萍.  含噪独立分量分析的期望最大化算法 . 电子科技大学学报, 2012, 41(4): 527-531. doi: 10.3969/j.issn.1001-0548.2012.04.009
    [12] 阎彬, 陈建军, 马洪波.  随机弹性杆在随机瞬态温度场下的热响应分析 . 电子科技大学学报, 2012, 41(4): 631-636. doi: 10.3969/j.issn.1001-0548.2012.04.030
    [13] 宋国明, 王厚军, 姜书艳, 刘红.  最小生成树SVM的模拟电路故障诊断方法 . 电子科技大学学报, 2012, 41(3): 412-417. doi: 10.3969/j.issn.1001-0548.2012.03.018
    [14] 罗航, 王厚军, 黄建国, 龙兵.  用递归BDD技术分析故障树 . 电子科技大学学报, 2011, 40(5): 726-731.
    [15] 龙航, 王文博.  HARQ过程条件错误概率分析 . 电子科技大学学报, 2010, 39(1): 41-44,49. doi: 10.3969/j.issn.1001-0548.2010.01.010
    [16] 姜群, 李祖枢, 欧阳, 董世都, 邱小平.  在子集条件约束下的最大熵分布及其应用 . 电子科技大学学报, 2008, 37(1): 94-96,123.
    [17] 李荣冰, 刘建业, 林雪原, 华冰, 刘瑞华.  梳状音叉MEMS陀螺非随机误差分析 . 电子科技大学学报, 2006, 35(6): 928-931.
    [18] 陈光宇, 黄锡滋, 唐小我.  故障树模块化分析系统可靠性 . 电子科技大学学报, 2006, 35(6): 989-992.
    [19] 曾成碧, 陈光.  可达树分析法及其在测试中的应用 . 电子科技大学学报, 1999, 28(5): 524-526.
    [20] 唐小我.  二度价格歧视情形下垄断厂商收益最大化条件 . 电子科技大学学报, 1997, 26(2): 194-198.
  • 加载中
计量
  • 文章访问数:  4856
  • HTML全文浏览量:  129
  • PDF下载量:  279
  • 被引次数: 0
出版历程
  • 刊出日期:  2016-02-15

统一框架的混合依存句法分析

doi: 10.3969/j.issn.1001-0548.2016.01.017
  • 中图分类号: TN912

摘要: 监督统计句法分析器的性能很大程度依赖于昂贵而有限的人工标注数据。为充分利用现有标注树库而不需额外设计句法分析器,该文提出了一种混合句法处理管线。该管线以基于最大生成树算法和线性链式条件随机场的句法分析器为基本框架,融合使用不同树库进行混合训练,综合利用不同树库对应的基线分析器解析的依存骨架,提取交叉信息,并在基本框架上构建了综合句法分析器。实验结果表明,该方法可以有效地提升单一树库的句法分析器的分析精度。

English Abstract

吴福祥, 周付根. 统一框架的混合依存句法分析[J]. 电子科技大学学报, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017
引用本文: 吴福祥, 周付根. 统一框架的混合依存句法分析[J]. 电子科技大学学报, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017
WU Fu-xiang, ZHOU Fu-gen. Unified Framework for Hybrid Dependency Parsin[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017
Citation: WU Fu-xiang, ZHOU Fu-gen. Unified Framework for Hybrid Dependency Parsin[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(1): 102-106. doi: 10.3969/j.issn.1001-0548.2016.01.017
参考文献 (16)

目录

    /

    返回文章
    返回