面向英语文章的词性标注算法

doi:10.13190/j.jbupt.2014.06.025

北京邮电大学学报 ›› 2014, Vol. 37 ›› Issue (6): 120-124.doi: 10.13190/j.jbupt.2014.06.025

面向英语文章的词性标注算法

谭咏梅, 吴坤

北京邮电大学智能科学与技术中心, 北京 100876

收稿日期:2013-07-10 出版日期:2014-12-28 发布日期:2014-12-28
作者简介:谭咏梅(1975-),女,副教授,硕士生导师,E-mail:ymtan@bupt.edu.cn.
基金资助:
国家自然科学基金项目(61273365)

A Part-of-Speech Tagging Method for English Essay

TAN Yong-mei, WU Kun

Center for Intelligence Science and Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2013-07-10 Online:2014-12-28 Published:2014-12-28

摘要/Abstract

摘要：

面向英语文章的词性标注是对英语文章实现自动批改的基础,虽然研究者对英语词性标注做了大量有益的研究,但是大多数的研究都面向英语为第一语言的用户,而面向英语为第二语言用户的相关研究则很少. 为此,对以英语为第二语言用户的英语文章进行了人工标注,在此基础上提出了一种面向英语文章的词性标注算法,融合了词聚类、无标语料统计信息、单词发音等特征. 实验结果表明,该算法能有效提高词性标注性能,标注正确率从94.49%可提高到97.07%.

关键词: 词性标注, 学生英语文章, 特征, 词聚类

Abstract:

Part-of-speech tagging for Chinese English learner language is the base of automated essay scoring system. Much of fruitful part-of-speech tagging researches researchers was done, however, most of them are focused on the English essays written by native speaker, there is no research about essays of Chinese English learner. A corpus of Chinese English learner essay are annotated, and a part-of-speech tagging algorithm for Chinese English learner language is presented. This algorithm uses rich features, such as unsupervised word clusters, unsupervised tag dictionary and phonetic normalization. Based on these rich features, the system outperforms the state-of-art tagging on the corpus, and the tagging accuracy is raised from 94.49% to 97.07%.

Key words: part-of-speech tagging, essays of learner, feature, word clustering

中图分类号:

TN911.22

谭咏梅, 吴坤. 面向英语文章的词性标注算法[J]. 北京邮电大学学报, 2014, 37(6): 120-124.

TAN Yong-mei, WU Kun. A Part-of-Speech Tagging Method for English Essay[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2014, 37(6): 120-124.

参考文献

[1] Kristina Toutanova, Dan Klein, Christopher D Manning, et al. Feature-rich part-of-speech tagging with a cyclic dependency network[C]//Proceedings of NAACL-HLT 2003. Los Angeles, California: Association for Computational Linguistics, 2003, 1: 173-180.

[2] Ana Daz-Negrillo, Detmar Meurers, Salvador Valera, et al. Towards interlanguagepos annotation for effective learner corpora in sla and flt[J]. Language Forum, 2010, 36: 1-15.

[3] Mitchell Marcus, Beatrice Santorini, Mary Ann Marcinkiewicz. Building a large annotated corpus of English: the penn treebank[J]. Computational Linguistics, 1993, 19: 313-330.

[4] 李红. 大学生英语写作常见错误归类分析[J]. 当代教育论坛: 学科教育研究, 2006, 8: 120-121. Li Hong. The common errors analysis of college englishwriting[J]. Forum on Contemporary Education, 2006, 8: 120-121.

[5] 张雷刚. 英语写作常见错误分析及教学建议[J]. 经济研究导刊, 2010, 19: 243-244. Zhang Leigang. Common errors in English writing and teaching suggestions[J]. Economic Research Guide, 2010, 19: 243-244.

[6] Yoav Goldberg, Michael Elhadad. An efficient algorithm for easy-first non-directional dependency parsing[C]//Proceedings of NAACL 2010. Los Angeles, California: Association for Computational Linguistics, 2010: 742-750.

[7] Jun'ichi Kazama, Jun'ichi Tsujii. Evaluation and extension of maximum entropy models with inequality constraints[C]//Proceedings of EMNLP 2003. Honolulu, Hawaii: Association for Computational Linguistics, 2003: 137-144.

[8] Peter F. Brown, Peter V. Desouza, Robert L. Mercer, et al. Vincent J. Della Pietra, and Jenifer C. Lai. Class-based n-gram models of natural language[J]. Computational Linguistics, 1992, 18(4): 467-479.

[9] Alan Ritter, Sam Clark, Mausam, et al. Named entity recognition in tweets: an experimental study[C]//Proceedings of EMNLP 2011. Honolulu, Hawaii: Association for Computational Linguistics, 2011: 1524-1534.

[10] Olutobi Owoputi, Brendan O'Connor, Chris Dyer, et al. Improved part-of-speech tagging for online conversational text with word clusters[C]//Proceedings of NAACL-HLT 2013. Los Angeles, California: Association for Computational Linguistics, 2013: 380-390.

[11] Adwait Ratnaparkhi. A maximum entropy model for part-of-speech tagging[C]//Proceedings of EMNLP 1997. Honolulu, Hawaii: Association for Computational Linguistics, 1996, 1: 133-142.

[12] Lawrence Phillips. Hanging on the Metaphone[J]. Computer Language, 1990, 7(12): 39-44.

[1]	张天魁蔡昌利骆晓亮朱禹涛. 基于多尺度特征Transformer的细粒度图像分类方法[J]. 北京邮电大学学报, 2023, 46(4): 70-75.
[2]	周雨昊孙哲吴晓非禹可. 基于门控特征融合的中文错别字纠正模型[J]. 北京邮电大学学报, 2023, 46(4): 91-96,122.
[3]	苏兴禹可吴晓非. 基于层次门控交互融合网络的谣言检测方法[J]. 北京邮电大学学报, 2023, 46(4): 97-102.
[4]	王延凯龙华邵玉斌杜庆治王瑶. 基于融合特征MGCC的语种识别方法[J]. 北京邮电大学学报, 2023, 46(2): 116-121.
[5]	张昊阁邵玉斌龙华杜庆治周大春. 基于Gammatone尺度功率规整系数谱图的语种识别[J]. 北京邮电大学学报, 2023, 46(2): 122-128.
[6]	胡敏熊思黄宏程张光华王春芳. 基于RAPNet的脑肿瘤MRI图像三维分割[J]. 北京邮电大学学报, 2023, 46(2): 91-97.
[7]	张雅斓班晓娟董子瑞. 面向单目视频的非牛顿流体仿真重建[J]. 北京邮电大学学报, 2023, 46(2): 109-115.
[8]	张昊阁邵玉斌龙华彭艺周大春. 基于对数Gammatone滤波器能量谱图的语种识别[J]. 北京邮电大学学报, 2023, 46(1): 38-43.
[9]	宋宇博高嘉振. 改进YOLOv3算法的交通多目标检测方法[J]. 北京邮电大学学报, 2022, 45(5): 103-108.
[10]	张小乾谈振王潇梁芹万黎明. 基于正交投影学习的图像特征提取算法[J]. 北京邮电大学学报, 2022, 45(5): 85-90,128.
[11]	李雪, 李晓艳, 王鹏, 孙梦宇, 吕志刚. 结合双注意力与特征融合的孪生网络目标跟踪[J]. 北京邮电大学学报, 2022, 45(4): 116-122.
[12]	武兴坤, 罗涛, 刘爱军, 杨明, 张文静. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[13]	武兴坤罗涛刘爱军杨明张文静李剑峰李文秀. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[14]	陈显露, 张天骐, 孟莹, 王晓烨. 带残余频偏的QPSK-DSSS信号伪码序列盲估计[J]. 北京邮电大学学报, 2022, 45(3): 90-95.
[15]	晁浩, 马庆敏, 刘永利. 利用卷积回声状态网络实现脑电情感识别[J]. 北京邮电大学学报, 2022, 45(2): 36-43.

面向英语文章的词性标注算法

A Part-of-Speech Tagging Method for English Essay

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价