时态信息的语义抽取与排序方法研究及系统实现

计算机工程与科学 ›› 2014, Vol. 36 ›› Issue (08): 1609-1614.

时态信息的语义抽取与排序方法研究及系统实现

舒忠梅1,左亚尧2,张祖传2

(1.中山大学教育学院，广东广州 510275；2.广东工业大学计算机学院，广东广州 510006)

收稿日期:2013-05-28 修回日期:2013-09-29 出版日期:2014-08-25 发布日期:2014-08-25
基金资助:
国家自然科学基金资助项目(60970044)；广东省自然科学基金资助项目(S2011040004281)

Study on extraction and ranking of temporal #br# semantics and system implementation

SHU Zhongmei1,ZUO Yayao2,ZHANG Zuchuan2

(1.School of Education,Sun YatSen University,Guangzhou 510275；
2.Faculty of Computer,Guangdong University of Technology,Guangzhou 510006,China)

Received:2013-05-28 Revised:2013-09-29 Online:2014-08-25 Published:2014-08-25

摘要/Abstract

摘要：

针对通用搜索引擎缺乏对网页内容的时态表达式的准确抽取及语义查询支持，提出时态语义相关度算法（TSRR）。在通用搜索引擎基础上添加了时态信息抽取和时态信息排序功能，通过引入时态正则表达式规则，抽取查询关键词和网页文档中的时态点或时态区间等时态表达式，综合计算网页内容的文本相关度和时态语义相关度，从而得到网页的最终排序评分。实验表明，应用TSRR算法可以准确而有效地匹配与时态表达式相关的关键词查询。

关键词: 时态语义, 信息抽取, 排序, 搜索引擎

Abstract:

General search engine lacks of extraction and retrieval of temporal semantic from the text content of the Web pages. To address the temporal query problem, the Temporal Semantic Relevancy Ranking (TSRR) algorithm is proposed by integrating the temporal information extraction and ranking functions. Firstly, the rule of the temporal regular expression is introduced to extract the temporal points or temporal intervals from the query keywords and the text content of the web pages. Secondly, the scores of web pages are reevaluated and the returned results are ranked according to the text relevancy and the temporal semantic relevancy. Experiments show that the TSRR algorithm precisely and effectively matches the keywords queries related to the temporal expression.

Key words: temporal semantic, information extraction, ranking, search engine

舒忠梅, 左亚尧, 张祖传. 时态信息的语义抽取与排序方法研究及系统实现[J]. 计算机工程与科学, 2014, 36(08): 1609-1614.

SHU Zhongmei, ZUO Yayao, ZHANG Zuchuan. Study on extraction and ranking of temporal #br# semantics and system implementation [J]. Computer Engineering & Science, 2014, 36(08): 1609-1614.

参考文献［15］

［1］	Alonso O, Gertz M, BaezaYates R. On the value of temporal information in information retrieval［J］. ACM SIGIR Forum, 2007, 41(2):3541.
［2］	Whiting S, Klampanos I A, Jose J M. Temporal pseudorelevance feedback in microblog retrieval ［C］∥Proc of the 34th European Conference on Advances in Information Retrieval,2012:522526.
［3］	Choi J, Croft W B. Temporal models for microblogs［C］ ∥Proc of the 21st ACM International Conference on Information and Knowledge Management, 2012:24912494.
［4］	Strotgen J, Alonso O, Gertz M. Identification of top relevant temporal expressions in documents ［C］∥Proc of the 2nd ACM Temporal Web Analytics Workshop, 2012:3340.
［5］	Kuzey E, Weikum G. Extraction of temporal facts and events from Wikipedia ［C］∥Proc of the 2nd ACM Temporal Web Analytics Workshop, 2012:2532.
［6］	Dakka W, Gravano L, lpeirotis P G. Answering general time sensitive queries［C］∥Proc of the 17th ACM Conference on Information and Knowledge Management, 2008:14371438.
［7］	Kage T, Sumiya K. A Web search method based on the temporal relation of query keywords［C］∥Proc of the 7th International Conference on Web Information Systems Engineering, 2006:515.
［8］	Li F, Yi K, Le W. Topk queries on temporal data ［J］. The VLDB Journal, 2010, 19(5):715733.
［9］	Campos R, Dias G, Jorge A, et al. Enriching temporal query understanding through date identification:How to tag implicit temporal queries?［C］ ∥Proc of the 2nd ACM Temporal Web Analytics Workshop, 2012:4148.
［10］	Kanhabua N, Nrvg K. Learning to rank search results for timesensitive queries ［C］∥Proc of the 21st ACM International Conference on Information and Knowledge Management, 2012:24632466.
［11］	Zhang Qiyu,Zhu Ling,Zhang Yaping.Summingup of studies on Chinese segmentation arithmetic［J］.Information Research,2008(11):5356.(in Chinese)
［12］	McCandless M, Hatcher E, Gospodnetic O. Lucene in action［M］.2nd ed. USA:Manning Publications Co.,2010.
［13］	Zuo Yayao, Tang Yong, Shu Zhongmei. Method of the subtraction operation between temporal points with granularities based on granularity hierarchy mapping［J］. Journal of Computer Research and Development, 2012,49(11):23202327.(in Chinese)
［14］	Zuo Yayao, Shu Zhongmei, Tang Yong. Exploration into granularity constraints and standardization of temporal primitives［J］. Journal of Chinese Computer Systems,2013,34(5):10701075.(in Chinese)
［15］	Zuo Yayao,Shu Zhongmei,Tang Yong.Research on qualitative relationship among temporal elements with temporal granularities constraint［J］. Computer Engineering and Science,2013,35(2):3440.(in Chinese)
	附中文参考文献：
［11］	张启宇,朱玲,张雅萍.中文分词算法研究综述［J］.情报探索,2008(11):5356.
［13］	左亚尧,汤庸,舒忠梅.基于粒度层次映射转换的时态粒点差运算方法［J］.计算机研究与发展,2012,49(11):23202327.
［14］	左亚尧,舒忠梅,汤庸.时态原语的粒度约束与规范化问题探讨［J］.小型微型计算机系统,2013,34(5):10701075.
［15］	左亚尧,舒忠梅,汤庸.时态粒度约束下的时态元素定性关系探讨［J］.计算机工程与科学,2013,35(2)：3440.

[1]	卓灵1，聂静1，肖静薇1，袁杨2，胡新1，陈柯1. 电力无线通信异构多网共存环境中的网络选择算法[J]. J4, 20160101, 38(01): 78-83.
[2]	曹军航, 黄瑞章, 白瑞娜, 赵建辉, . DCsR：一种面向中文文本的集成式纠错框架[J]. 计算机工程与科学, 2023, 45(02): 370-380.
[3]	何海江. 融合语句复杂度的软件错误定位轻量级方法[J]. 计算机工程与科学, 2022, 44(12): 2187-2195.
[4]	张勇, 张曦, 万云博, 何先耀, 赵钟, 卢宇彤. 非结构有限体积CFD计算的网格重排序优化[J]. 计算机工程与科学, 2022, 44(10): 1721-1729.
[5]	陈华烨, 汪海涛, 姜瑛, 陈星. 基于排序学习的构件检索方法的研究[J]. 计算机工程与科学, 2021, 43(06): 1006-101.
[6]	刘亚波, 吴秋轩. 基于长短时记忆网络的电商大数据同一性标定[J]. 计算机工程与科学, 2021, 43(03): 407-415.
[7]	杨柳, 金培权. 面向DRAM和NVM异构混合内存架构的排序连接算法优化[J]. 计算机工程与科学, 2021, 43(02): 191-198.
[8]	肖满, 丁璐, 张怡. 带两个服务等级的3台机半在线算法[J]. 计算机工程与科学, 2020, 42(12): 2252-2258.
[9]	官蕊, 丁家满, 贾连印, 游进国, 姜瑛, . 基于强化学习的多样性文档排序算法[J]. 计算机工程与科学, 2020, 42(09): 1697-1703.
[10]	朱国晖，张茵，刘秀霞，孙天骜. 基于两次优先级排序的虚拟网络映射算法[J]. 计算机工程与科学, 2020, 42(05): 795-802.
[11]	李茜, 周华健, 杨浩运, 殷海兵. 一种基于listwise的在线学习书目排序检索算法[J]. 计算机工程与科学, 2020, 42(04): 749-754.
[12]	王鑫, 陈建凯, 翟俊海, . 区间值属性单调决策树算法的扩展[J]. 计算机工程与科学, 2020, 42(03): 557-563.
[13]	张卫祥，齐玉华，魏波，张敏，窦朝晖. 基于蚁群算法的测试用例优先排序[J]. 计算机工程与科学, 2020, 42(02): 241-249.
[14]	刘少楠，李玲，苑迎，蒋国佳，王聪，吕艳霞. 基于节点连通性排序的虚拟网络映射算法[J]. 计算机工程与科学, 2019, 41(12): 2101-2109.
[15]	孟昱煜，陈绍立，刘兴长. 面向排序学习的层次聚类特征选择算法[J]. 计算机工程与科学, 2019, 41(12): 2211-2216.