基于浅层句法特征的评价对象抽取研究

徐冰; 赵铁军; 王山雨; 郑德权

doi:10.3724/SP.J.1004.2011.01241

基于浅层句法特征的评价对象抽取研究

doi: 10.3724/SP.J.1004.2011.01241

1.
哈尔滨工业大学计算机科学与技术学院机器智能与翻译研究室哈尔滨 150001

详细信息

通讯作者:
徐冰博士研究生.主要研究方向为自然语言处理和情感分析. E-mail: xb@mtlab.hit.edu.cn

计量
- 文章访问数: 2295
- HTML全文浏览量: 82
- PDF下载量: 1376
- 被引次数: 0
出版历程
- 收稿日期: 2010-11-22
- 修回日期: 2011-03-24
- 刊出日期: 2011-10-20

Extraction of Opinion Targets Based on Shallow Parsing Features

1.
Machine Intelligence and Translation Laboratory, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001

摘要

摘要: 随着网络评论文本数量的快速增长,文本情感分析越来越受到研究者的广泛关注. 句子级文本情感分析就是对主观性文本进行细粒度的挖掘,有重要的研究价值. 评论句中的评价对象抽取是句子级情感分析要研究的关键问题之一. 为了提高评价对象抽取的性能,本文提出在系统模型的训练过程中引入浅层句法信息和启发式位置信息,同时在不增加领域词典的情况下, 有效提高系统的精确率.实验结果表明,将本文提出的特征引入到条件随机域模型和对比模型后,系统的各项指标均有所提高, 并且条件随机域模型的结果优于对比模型.同时,将条件随机域模型的结果与2008年国内中文评测的最大值比较,其F值超过最大值 5%.
- 文本情感分析 /
- 意见挖掘 /
- 评价对象抽取 /
- 浅层句法特征 /
- 位置特征
Abstract: With the rapid development of the world wide web, more and more common users express their opinions on the web and many researchers pay more attentions to sentiment analysis. Fine-grained sentiment analysis on sentence level is very important. The extraction of opinion targets from opinion sentence is the key issue to sentence level of sentiment analysis. To improve the performance of opinion targets extraction, this paper proposes to integrate shallow parsing features and heuristic position information for modeling of the training process without introducing domain lexicon. The experiment results show that after adding the proposed features, nearly all specifications of both conditional random fields and contrast model are improved, and the results of conditional random fields are more efficient than that of the contrast model. Meanwhile, compared with the best results of the 2008 Chinese opinion analysis evaluation, the F measures of conditional random fields are 5% higher than the maximum value.
- Sentiment analysis /
- opinion mining /
- opinion targets extraction /
- shallow parsing feature /
- position feature

HTML全文

参考文献(1)

[1]

Zhang L, Liu B, Lim S H, O'Brien-Strain E. Extracting and ranking product features in opinion documents. In: Proceedings of the 23rd International Conference on Computational Linguistics: Posters. Stroudsburg, USA: Association for Computational Linguistics, 2010. 1462-1470[2] Wan X J. Co-training for cross-lingual sentiment classification. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language. Stroudsburg, USA: Association for Computational Linguistics, 2009. 235-243[3] Zhao Yan-Yan, Qin Bing, Liu Ting. Integrating intra-and inter-document evidences for improving sentence sentiment classification. Acta Automatica Sinica, 2010, 36(10): 1417-1425[4] Pang B, Lillian L. A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2004. 271-278[5] Swati T, Barbara D E. Generating fine-grained reviews of songs from album reviews. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2010. 1376-1385[6] Niklas J, Iryna G. Using anaphora resolution to improve opinion target identification in movie reviews. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: Association for Computational Linguistics, 2010. 263-268[7] Zhao Yan-Yan, Qin Bing, Liu Ting. Sentiment analysis. Journal of Software, 2010, 21(8): 1834-1848(赵妍妍, 秦兵, 刘挺. 文本情感分析. 软件学报, 2010, 21(8): 1834-1848)[8] Liu B, Hu M Q, Cheng J S. Opinion observer: analyzing and comparing opinions on the Web. In: Proceedings of the 14th International Conference on World Wide Web. Chiba, Japan: ACM, 2005. 342-351[9] Popescu A M, Etzioni O. Extracting product features and opinions from reviews. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing. Stroudsburg, USA: Association for Computational Linguistics, 2005. 339-346[10] Yao Tian-Fang, Nie Qing-Yang, Li Jian-Chao, Li Lin-Lin, Lou De-Cheng, Chen Ke, Fu Yu. An opinion mining system for Chinese automobile reviews. In: Proceedings of the 25th Anniversary Chinese Information Processing Society of China. Beijing, China: Tsinghua University Press, 2006. 260-281(姚天昉, 聂青阳, 李建超, 李林琳, 娄德成, 陈珂, 付宇. 一个用于汉语汽车评论的意见挖掘系统. 中国中文信息学会二十五周年学术会议. 北京, 中国: 清华大学出版社, 2006. 260-281)[11] Zhang S, Jia W J, Xia Y J, Meng Y, Yu H. Opinion analysis of product reviews. In: Proceedings of the 6th International Conference on Fuzzy Systems and Knowledge Discovery. Tianjin, China: IEEE, 2009. 591-595[12] Liu Hong-Yu, Zhao Yan-Yan, Qin Bing, Liu Ting. Comment target extraction and sentiment classification. Journal of Chinese Information Processing, 2010, 24(1): 84-88(刘鸿宇, 赵妍妍, 秦兵, 刘挺. 评价对象抽取及其倾向性分析. 中文信息学报, 2010, 24(1): 84-88)[13] Lafferty J D, McCallum A, Pereira F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference Machine Learning. Williamstown, Australia: Morgan Kaufmann, 2001. 282-289[14] Zhu C H, Zhao T J, Yu M O. Chinese word segmenter based on discriminative classifiers integration. Journal of Information and Computational Science, 2009, 6(3): 1155-1162[15] Zhao Jun, Xu Hong-Bo, Huang Xuan-Jing, Tan Song-Bo, Liu Kang, Zhang Qi. Overview of Chinese opinion analysis evaluation 2008. In: Proceedings of the 1st Chinese Opinion Analysis Evaluation. Beijing, China: The Professional Committee of Information Retrieval, 2008. 1-20(赵军, 许洪波, 黄萱菁, 谭松波, 刘康, 张奇. 中文倾向性分析评测技术报告. 第一届中文倾向性分析评测研讨会. 北京, 中国: 信息检索专业委员会, 2008. 1-20)

施引文献

资源附件(0)

访问统计