本文關(guān)鍵詞：基于Markov網(wǎng)絡(luò)的結(jié)果重排技術(shù)，由筆耕文化傳播整理發(fā)布。

下載： 訪問網(wǎng)刊     導(dǎo)出： EndNote (RIS)

摘要：

信息檢索中通過網(wǎng)頁鏈接信息提取文檔內(nèi)部關(guān)系進(jìn)行搜索結(jié)果重排可以提升檢索系統(tǒng)的性能.通過Markov網(wǎng)絡(luò)來展現(xiàn)文檔內(nèi)部關(guān)系,該網(wǎng)絡(luò)更直觀地解釋了文檔間的語義相關(guān)性,利用這種文檔內(nèi)部語義關(guān)系計(jì)算文檔重要性對檢索結(jié)果進(jìn)行重排.根據(jù)文檔分布特征闡述了Markov文檔網(wǎng)絡(luò)的構(gòu)造算法,討論了Top-k及其相關(guān)文檔的重要性評分算法,修正初始檢索的文檔評分.通過這種方式,既保持了文檔圖的查詢相關(guān)性,又豐富了文檔內(nèi)部關(guān)系,擴(kuò)大了重排序范圍.實(shí)驗(yàn)表明,在多個(gè)標(biāo)準(zhǔn)文檔集上基于Markov網(wǎng)絡(luò)的結(jié)果重排技術(shù)對檢索性能有較大的穩(wěn)定提升.

關(guān)鍵詞： 信息檢索   Markov網(wǎng)絡(luò)   結(jié)果重排  

基金：

國家自然科學(xué)基金(61201456)

Information Center, Jiangxi University of Science and Technology, Ganzhou 341000,P.R.China   Center of Arts Complex Lab, Jiangxi Science & Technology Normal University, Nanchang 330038 ,P.R.China   Key Lab of Optic-electronic & Communication, Jiangxi Science & Technology Normal University, Nanchang 330038 ,P.R.China  

Abstract：

Keywords：

[1]RIJSBERGEN van.A new theoretical framework for information retrieval[C]//In Proceedings of 1986 ACM Conference on Research and Development in Information Retrieval.Italy:Pisa,1986:194-200.

[2]HE Ben,OUNIS Ladh.Studying Query Expansion Effectiveness[J].Advance in Information Retrieval,2009,5578:611-619.

[3]MA Yunlong,LIN Hongfei,JIN Song.A RevisedSimRank Approach for query expansion[J].Information Retrieval Technology,2010,6458:564-575.

[4]CARPINETO C,ROMANO G.A survey of automatic query expansion in information retrieval[J].Journal of ACM Computing Surveys,2012,44(1):3-6.

[5]CROFT B.A cluster based resampling method for pseudo-relevance feedback[C]//Proceeding s of the 31 st annual international ACM SIGIR conference on Research and development in information retrieval.Singapore:ACM.2008:235-242.

[6]KURLAND O,LEE L.PageRank without hyperlinks:Structural re-ranking using links induced by language models[J].Information Processing and Management,2010,28(4):1-14.

[7]YE Z,HUANG J,LIN H.Incorporating rich features to boost information retrieval performance:A SVM-regression based re-ranking approach[J].Expert Systems with Applications,2011,38 (6):7569-7574.

[8]PAGE L,BRIN S.The PageRank Citation Ranking:Bringing Order to the Web[EB/OL].(2008-12-28)[2013-01-02].,edu:8090/422/.

[9]曹瑛,王明文,陶紅亮.基于Markov網(wǎng)絡(luò)的檢索模型[J].山東大學(xué)學(xué)報(bào):理學(xué)版,2006,3 (41):126-130.CAO Ying,WANG Mingwen,TAO Hongliang.Information retrieval model based on Markov Network[J].Journal of Shandong University:Natural Science Edition,2006,3(41):126-130.

[10]左家莉.信息檢索中Markov網(wǎng)絡(luò)圖模型研究[D].江西:江西財(cái)經(jīng)大學(xué),2011.ZUO Jiali.The Study of Markov Network Graph Model in Information Retrieval[D].Jiangxi:Jiangxi University of Finance and Economic,2011.

[11]WANG Xuanhui,FANG Hui,ZHAI Chengxiang.A study of methods for negative relevance feedback[C]//Proceeding s of the 31st annual international ACM SIGIR conference on Research and development in information retrieval.Singapore:ACM.2008:219-226.

[12]ROBERTSON S,WAKER S.Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval[EB/OL].(2008-07-12)[2013-02-01].

  本文關(guān)鍵詞：基于Markov網(wǎng)絡(luò)的結(jié)果重排技術(shù)，由筆耕文化傳播整理發(fā)布。