Topic clause identification method based on specific features

doi:10.11772/j.issn.1001-9081.2014.05.1345

Journal of Computer Applications ›› 2014, Vol. 34 ›› Issue (5): 1345-1349.DOI: 10.11772/j.issn.1001-9081.2014.05.1345

• Artificial intelligence • Previous Articles Next Articles

Topic clause identification method based on specific features

JIANG Yuru¹,²,SONG Rou¹,³

1. College of Computer Science, Beijing University of Technology, Beijing 100022, China;
2. Computer School, Beijing Information Science and Technology University, Beijing 100101, China;
3. College of Information Science, Beijing Language and Culture University, Beijing 100083, China

Received:2013-10-25 Revised:2014-01-07 Online:2014-05-30 Published:2014-05-01
Contact: JIANG Yuru

基于细粒度特征的话题句识别方法

蒋玉茹¹,²,宋柔¹,³

1. 北京工业大学计算机学院，北京 100022
2. 北京信息科技大学计算机学院，北京 100101；
3. 北京语言大学信息科学学院，北京 100083

通讯作者: 蒋玉茹
作者简介:蒋玉茹(1978-)，女，辽宁沈阳人，讲师，博士研究生，CCF会员，主要研究方向：自然语言处理；宋柔(1946-)，男，江苏苏州人，教授， CCF会员，主要研究方向：自然语言处理。
基金资助:
国家自然科学基金资助项目;北京市教委科研计划面上项目

Abstract

Abstract:

When identifying the Topic Clause (TC) of Punctuation Clause (PClause), the brute-force method to generate Candidate Topic Clause (CTC) causes high time consumption and low accuracy of the identification system. A new CTC generating method was proposed, which used specific features such as the PClause location in the text, the grammatical features of the topic and the adjacent features of topic and its comment. The experimental result shows that the improved method can not only improve the efficiency of the system by reducing the number of CTCs, but also make the accuracy of TC identification for single PClause and PClause sequence increase by 0.96 percentage points and 1.31 percentage points respectively over the current state.

摘要：

话题句（TC）识别中采用穷举方法生成标点句的候选话题句（CTC）影响系统的执行效率和话题句识别的准确率。提出一种新的候选话题句生成方法，利用标点句在篇章中的位置特征、话题的语法特征以及话题串与说明的邻接性特征，指导候选话题句的生成过程。实验结果表明，该方法减少了候选话题句的个数，提高了系统效率。而且，通过与基于穷举式候选话题句生成策略的话题句识别工作进行对比，该方法使单个标点句话题句识别的准确率提高了0.96个百分点，使标点句序列话题句识别的准确率提高了1.31个百分点。

CLC Number:

TP391

JIANG Yuru SONG Rou. Topic clause identification method based on specific features[J]. Journal of Computer Applications, 2014, 34(5): 1345-1349.

蒋玉茹宋柔. 基于细粒度特征的话题句识别方法[J]. 计算机应用, 2014, 34(5): 1345-1349.

References

［1］ZHANG R. The research about the constraint rules of syntax relation in cross-punctuation sentence in written mordern Chinese ［D］. Beijing: Beijing Language and Culture University, 2007.(张瑞朋.现代汉语书面语中跨标点句句法关系约束条件的研究［D］.北京：北京语言大学, 2007.)
［2］HUANG J, SONG R. A research on punctuation annotation ［C］// Proceedings of the 9th China National Conference on Computational Linguistics. Beijing: Tsinghua University Press, 2007:350-355.(黄健传,宋柔.标点句标注研究［C］// 第九届全国计算语言学学术会议论文集.北京：清华大学出版社,2007:350-355.)
［3］SONG R. A research on the properties of syntactic relation between P-clauses in modern Chinese ［J］. Chinese Teaching in the World, 2008,2:26-44.(宋柔.现代汉语跨标点句句法关系的性质研究［J］. 世界汉语教学,2008,2:26-44.)
［4］SONG R, JIANG Y, WANG J. On generalized-topic-based Chinese discourse structure ［C］// SIGHAN 2010: Proceedings of CIPS-SIGHAN Joint Conference on Chinese Language Processing. Beijing：Tsinghua University Press, 2010:23-33.
［5］SONG R. A research on generalized topic structure of Chinese text ［R］. Beijing: Beijing Language and Culture University, 2012.(宋柔.汉语篇章广义话题结构研究［R］.北京: 北京语言大学, 2012.)
［6］JIANG Y, SONG R. Topic clause identification based on generalized topic theory ［J］. Journal of Chinese Information Processing, 2012,26(5):114-119.(蒋玉茹,宋柔.基于广义话题理论的话题句识别［J］.中文信息学报,2012,26(5):114-119.)
［7］JIANG Y, SONG R. Optimization of candidate topic clause evaluation function in topic clause identification ［J］. Journal of Beijing University of Technology, 2014,40(1):43-48.(蒋玉茹, 宋柔.话题句识别中候选话题句评估函数的优化［J］.北京工业大学学报,2014,40(1):43-48.)
［8］GILLELAND M. Levenshtein distance, in three flavors ［EB/OL］. ［2013-02-04］. http://people.cs.pitt.edu/~kirk/cs1501/Pruhs/Spring2006/assignments/editdistance/Levenshtein%20Distance.htm.
［9］HU Q. Encyclopedia of China ［M/CD］. Beijing: Encyclopedia of China Publishing House, 1999.(胡乔木.中国大百科全书:图文数据光盘［M/CD］.北京：中国大百科全书出版社,1999. )
［10］KOHAVI R. A study of cross-validation and bootstrap for accuracy estimation and model selection ［C］// IJCAI '95: Proceedings of the 14th International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann, 1995,2:1137-1143.
［11］JIANG Y, SONG R. Topic structure identification of PClause sequence based on generalized topic theory ［C］// Proceedings of the 2012 1st CCF Conference on Natural Language Processing and Chinese Computing. Berlin: Springer-Verlag, 2012:85-96.

[1]	. Pavement defect detection algorithm with enhanced morphological perception [J]. Journal of Computer Applications, 0, (): 0-0.
[2]	YANG Jianfeng, CHEN Bin, LI Yuxuan. Self-supervised point cloud anomaly detection method based on point cloud reconstruction [J]. Journal of Computer Applications, 0, (): 0-0.
[3]	XUE Zhenhua, LI Qiang, HUANG Chao. Vision foundation model-driven pixel-level image anomaly detection model [J]. Journal of Computer Applications, 0, (): 0-0.
[4]	. Binocular vision object location algorithm for robot arm grasping [J]. Journal of Computer Applications, 0, (): 0-0.
[5]	. Multi-attention contrastive learning for infrared small target detection [J]. Journal of Computer Applications, 0, (): 0-0.
[6]	LI Zhonghua, ZHONG Gengxin, FAN Ping, ZHU Hengliang. Camouflaged object detection by boundary mining and background guidance [J]. Journal of Computer Applications, 0, (): 0-0.
[7]	. Multi-view difficult airway recognition based on discriminant region guidance [J]. Journal of Computer Applications, 0, (): 0-0.
[8]	. Privacy preserving localization of surveillance images based on large vision models [J]. Journal of Computer Applications, 0, (): 0-0.
[9]	. Gravity data denoising method based on multilevel wavelet residual network#br# #br# [J]. Journal of Computer Applications, 0, (): 0-0.
[10]	. Data augmentation method for abnormal passenger behavior in elevators based on dynamic graph convolutional network [J]. Journal of Computer Applications, 0, (): 0-0.
[11]	. Text-based person retrieval method based on multi-granularity shared semantic center association [J]. Journal of Computer Applications, 0, (): 0-0.
[12]	ZHANG Qing, YANG Fan, FANG Yuhan. Chinese Spelling Correction Algorithm Based on Multi-Modal Information Fusion [J]. Journal of Computer Applications, 0, (): 0-0.
[13]	WANG Hao, WANG Jinwei, CHENG Xin, ZHANG Jiawei, WU Hao, LUO Xiangyang, MA Bin. A Review of JPEG Recompression Forensics for Color Images [J]. Journal of Computer Applications, 0, (): 0-0.
[14]	. Distribution adaptation and dynamic curriculum pseudo-labeling framework for semi-supervised fire detection [J]. Journal of Computer Applications, 0, (): 0-0.
[15]	. Multimodal harmful content detection method based on weakly supervised modality semantic enhancement [J]. Journal of Computer Applications, 0, (): 0-0.

Topic clause identification method based on specific features

基于细粒度特征的话题句识别方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics