一种新型的中文产品评论微摘要方法研究
PDF下载 (355)赵福青 1,刘柏嵩 2*,葛文镇 1.一种新型的中文产品评论微摘要方法研究[J].宁波大学学报(理工版),2014,27(04):38-41.DOI:
ZHAO Fu-qing 1,LIU Bai-song 2*,GE Wen-zhen 1.Micro-abstract of Chinese Product Reviews: A Novel Approach[J].Journal of Ningbo University(Natural Science & Engineering Edition),2014,27(04):38-41.DOI:
| Title: | Micro-abstract of Chinese Product Reviews: A Novel Approach |
| 作者: | 赵福青 1, 刘柏嵩 2*, 葛文镇 1 |
| Author(s): | ZHAO Fu-qing 1, LIU Bai-song 2*, GE Wen-zhen 1 |
| 关键词: | 产品评论挖掘; 无监督学习; 微摘要 |
| Keywords: | web N-gram; product reviews mining; unsupervised approach; micro-abstract |
| 分类号: | TP391.1 |
| 文献标识码: | A |
| 摘要: | 提出一种新的无监督的方法, 对网络上存在的大量中文产品评论信息进行处理, 生成简洁的非结构化的可读性强且具有代表性、简洁性的理解式评论微摘要. 用N-gram语言模型来衡量可读性, 用改进的点间互信息函数来衡量代表性, 用同义词词林来计算词语相似度; 将这种产品评论微摘要问题归结为优化问题, 试图寻找具有可读性和代表性的简洁、低冗余的词组, 并提出了一个启发式算法来解决这个优化问题. |
| Abstract: | This paper presents a new unsupervised approach to generate micro-abstract of Chinese product reviews, mainly focusing on generating the readable, representative, concise and unstructured abstractive summaries. We model the readability with an N-gram language model, measure representative impact based on a modified mutual information function, and calculate words similarity with Tongyici Cilin. We also formulate the addressed issue as an optimization problem in a move to seek a set of concise and non-redundant phrases that are readable and can represent key opinions in text. In the end, we propose the heuristic algorithms to efficiently solve the formulated optimization problem. |
| 参考文献 /References: | [1] 郗亚辉, 张明, 袁方, 等. 产品评论挖掘研究综述[J]. 山东大学学报: 理工版, 2011, 46(5):16-23. [2] Li Zhuang, Jing Feng, Zhu Xiaoyan. Movie review mining and summarization[C]. Proceedings of the 15th ACM international conference on Information and knowledge management ACM, 2006:43-50. [3] Liu Bing, Hu Mingqing, Cheng Junsheng. Opinion observer: Analyzing and comparing opinions on the web[C]. Proceedings of the 14th international conference on World Wide Web, ACM, 2005:342-351. [4] Hu Mingqing, Liu Bing. Mining and summarizing customer reviews[C]. Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2004:168-177. [5] Lu Yue, Zhai ChengXiang, Sundaresan N. Rated aspect summarization of short comments[C]. Proceedings of the 18th international conference on World wide web, ACM, 2009:131-140. [6] Ganesan K, Zhai Chengxiang, Han J. Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions[C]. Proceedings of the 23rd International Conference on Computational Linguistics, Association for Computational Linguistics, 2010:340-348. [7] 田久乐, 赵蔚. 基于同义词词林的词语相似度计算方法[J]. 吉林大学学报: 信息科学版, 2010, 28(6):602- 608. [8] Terra E, Clarke C L. Frequency estimates for statistical word similarity measures[C]. Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, 2003:165-172. [9] Wang Kuansan, Christopher T, Evelyne V, et al. An over- view of microsoft web N-gram corpus and applications [C]. Proceedings of the NAACL HLT 2010 Demonstra- tion Session, Association for Computational Linguistics, 2010:45-48. |
| 备注/Memo: | 收稿日期: 2013-12-31. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/基金项目: 浙江省部级实验室开放基金（B2014）.第一作者: 赵福青（1989－）, 女, 山东临沂人, 在读硕士研究生, 主要研究方向: 数据挖掘与评论挖掘. E-mail: zhaofuqing90@126.com*通信作者: 刘柏嵩（1971－）, 男, 安徽安庆人, 博士/研究员, 主要研究方向: 人工智能及计算机网络. E-mail: lbs@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
