您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

山东大学学报(理学版) ›› 2015, Vol. 50 ›› Issue (03): 6-10.doi: 10.6040/j.issn.1671-9352.3.2014.284

• 论文 • 上一篇    下一篇

融合词频特性及邻接变化数的微博新词识别

周超, 严馨, 余正涛, 洪旭东, 线岩团   

  1. 昆明理工大学信息工程与自动化学院计算机系, 云南省计算机技术应用重点实验室, 云南 昆明 650500
  • 收稿日期:2014-09-19 修回日期:2015-01-16 出版日期:2015-03-20 发布日期:2015-03-13
  • 作者简介:周超(1989- ),男,硕士研究生,研究方向为机器翻译.E-mail:kg_yanxin@sina.com
  • 基金资助:
    国家自然科学基金资助项目(61462055,61462054,61175068,61363044)

Weibo new word recognition combining frequency characteristic and accessor variety

ZHOU Chao, YAN Xin, YU Zheng-tao, HONG Xu-dong, XIAN Yan-tuan   

  1. School of Information Engineering and Automation of Computer Science, Kunming University of Science and Technology; Key Lab of Computer Technologies Application of Yunnan Province and Kunming, Kunming 650500, Yunnan, China
  • Received:2014-09-19 Revised:2015-01-16 Online:2015-03-20 Published:2015-03-13

摘要: 大量的新词伴随着微博的快速发展而产生,这些新词具有传播速度快及与其他词组合方式灵活的特点,而且在进行分词处理时容易被切分为不同的字符串。提出了一种融合词频特性及邻接变化数的微博新词识别方法。该方法首先对大规模的微博语料进行分词,然后将在两停用词间的相邻字串两两组合,根据组合后的字串频率统计取得新词候选串,再通过组合成词规则进行筛选获得候选新词,最后通过词的邻接域变化特性去除垃圾串获得新词。利用该方法在COAE 2014评测任务上进行了新词的发现实验,准确率达到36.5%,取得了较好的成绩。

关键词: 邻接变化数, 微博新词, 成词规则, 字串频率统计

Abstract: Along with the rapid development of Weibo, a lot of new words have appeared. These words have characteristic that spread fast and flexible combination with other words. They are easy to be cut apart into different string in segmentation processing. Therefore a new word recognition method that combines word frequency characteristics and accessor variety was proposed. The first step was to segment the large scale Weibo sentences into words, and then combine the two adjacent strings between stop words. The new word candidate strings could be obtained according to the string frequency of the combination. After the filtration through the word formation rules, the candidate new words would be found. Finally, through the characteristics of the word accessor variety, the garbage string was removed to get the new words. Experiments of new word recognition on COAE 2014 task 3 show that the accuracy can reach 36.5% and this method has a good performance.

Key words: Weibo new words, string frequency statistics, accessor variety, word formation rules

中图分类号: 

  • TP391
[1] LING G C, ASAHARA M, MATSUMOTO Y. Chinese unknown word identification using character-based tagging and chunking[C]//Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2003:197-200.
[2] 周正宇, 李宗葛.一种新的基于统计的词典扩展方法[J].中文信息学报, 2001, 15(5):46-51. ZHOU Zhengyu, LI Zongge. A new statistical method of automatic lexicon augmentation[J]. Journal of Chinese Information Processing, 2001, 15(5):46-51.
[3] WANG Aobo, KAN Min-Yen.Mining informal language from Chinese microtext: joint word recognition and segmentation[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2013:731-741.
[4] 郑家恒, 李文花. 基于构词法的网络新词自动识别初探[J]. 山西大学学报:自然科学版, 2002, 25(2):115-119. ZHENG Jiaheng, LI Wenhua. A study on automatic identification for internet new words according to word-building rule[J].Journal of Shanxi University: Natural Science Edition, 2002, 25(2):115-119.
[5] 崔世起,刘群,孟遥,等.基于大规模语料库的新词检测[J].计算机研究与发展,2006, 43(5):927-932. CUI Shiqi, LIU Qun, MENG Yao, et al. New word detection based on large-scale corpus[J]. Journal of Computer Research and Development, 2006, 43(5):927-932.
[6] 刘建舟, 何婷婷,骆昌日.基于语料库和网络的新词自动识别[J].计算机应用,2004, 24(7):132-134. LIU Jianzhou, HE Tingting, LUO Changri. Automatic new words detection based on corpus and web[J]. Journal of Computer Applications, 2004, 24(7):132-134.
[7] 邹纲,刘洋,刘群,等.面向Internet的中文新词语检测[J]. 中文信息学报,2004,18(6):1-9. ZOU Gang, LIU Yang, LIU Qun, et al. Internet-oriented Chinese new words detection[J]. Journal of Chinese Information Processing, 2004, 18(6):1-9.
[8] 何赛克,王小捷,董远,等.归一化的邻接变化数方法在中文分词中的应用[J].中文信息学报,2010,24(1):15-19. HE Saike, WANG Xiaojie, DONG Yuan, et al.Apply normalized accessor variety in Chinese word segmentation[J]. Journal of Chinese Information Processing, 2010, 24(1):15-19.
[9] FENG Haodi, CHEN Kang, KIT Chunyu, et al. Unsupervised segmentation of Chinese corpus using accessor variety[C]//Proceeding of the 1st International Joint Conference on Natural Language Processing-IJCNLP 2004. Berlin: Springer, 2005:694-703.
[1] 龚双双,陈钰枫,徐金安,张玉洁. 基于网络文本的汉语多词表达抽取方法[J]. 山东大学学报(理学版), 2018, 53(9): 40-48.
[2] 余传明,左宇恒,郭亚静,安璐. 基于复合主题演化模型的作者研究兴趣动态发现[J]. 山东大学学报(理学版), 2018, 53(9): 23-34.
[3] 严倩,王礼敏,李寿山,周国栋. 结合新闻和评论文本的读者情绪分类方法[J]. 山东大学学报(理学版), 2018, 53(9): 35-39.
[4] 原伟,唐亮,易绵竹. 基于本体的俄文新闻话题检测设计与实现[J]. 山东大学学报(理学版), 2018, 53(9): 49-54.
[5] 廖祥文,张凌鹰,魏晶晶,桂林,程学旗,陈国龙. 融合时间特征的社交媒介用户影响力分析[J]. 山东大学学报(理学版), 2018, 53(3): 1-12.
[6] 余传明,冯博琳,田鑫,安璐. 基于深度表示学习的多语言文本情感分析[J]. 山东大学学报(理学版), 2018, 53(3): 13-23.
[7] 张军,李竞飞,张瑞,阮兴茂,张烁. 基于网络有效阻抗的社区发现算法[J]. 山东大学学报(理学版), 2018, 53(3): 24-29.
[8] 庞博,刘远超. 融合pointwise及深度学习方法的篇章排序[J]. 山东大学学报(理学版), 2018, 53(3): 30-35.
[9] 陈鑫,薛云,卢昕,李万理,赵洪雅,胡晓晖. 基于保序子矩阵和频繁序列模式挖掘的文本情感特征提取方法[J]. 山东大学学报(理学版), 2018, 53(3): 36-45.
[10] 王彤,马延周,易绵竹. 基于DTW的俄语短指令语音识别[J]. 山东大学学报(理学版), 2017, 52(11): 29-36.
[11] 张晓东,董唯光,汤旻安,郭俊锋,梁金平. 压缩感知中基于广义Jaccard系数的gOMP重构算法[J]. 山东大学学报(理学版), 2017, 52(11): 23-28.
[12] 孙建东,顾秀森,李彦,徐蔚然. 基于COAE2016数据集的中文实体关系抽取算法研究[J]. 山东大学学报(理学版), 2017, 52(9): 7-12.
[13] 王凯,洪宇,邱盈盈,王剑,姚建民,周国栋. 一种查询意图边界检测方法研究[J]. 山东大学学报(理学版), 2017, 52(9): 13-18.
[14] 张帆,罗成,刘奕群,张敏,马少平. 异质搜索环境下的用户偏好性预测方法研究[J]. 山东大学学报(理学版), 2017, 52(9): 26-34.
[15] 杨艳,徐冰,杨沐昀,赵晶晶. 一种基于联合深度学习模型的情感分类方法[J]. 山东大学学报(理学版), 2017, 52(9): 19-25.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!