Skip to main navigation Skip to search Skip to main content

Search results optimization method combined with multi-features

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The optimization of search results has always been the research hotspot in the area of search engine. More concretely, topic partition by clustering proved to be a good way. However, the clusters, some of which still contain a lot of documents, implicitly limit the users' retrieval speed. Meanwhile we find that the information of documents' features have good effects on the document ranking. To address the issue, we try to apply the multi-features to search results after the process of clustering. Statistic and semantic information of the multi-features are fully used to re-rank the documents. Related experiments show that our approach outperforms that of single clustering much. The evaluation indicators' rising shows that the Top N results satisfy the users' need more.

Original languageEnglish
Title of host publicationProceedings - 2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011
Pages1167-1171
Number of pages5
DOIs
StatePublished - 2011
Event2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11 - Shanghai, China
Duration: 26 Jul 201128 Jul 2011

Publication series

NameProceedings - 2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011
Volume2

Conference

Conference2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11
Country/TerritoryChina
CityShanghai
Period26/07/1128/07/11

Keywords

  • Hownet
  • clustering
  • multi-features
  • re-ranking
  • semantic
  • statistic

Fingerprint

Dive into the research topics of 'Search results optimization method combined with multi-features'. Together they form a unique fingerprint.

Cite this