Speech tagging based improvement of the RSS polymerization news

Ying Bi, Yixin Jing, Peijun Ma, Doo Kwon Baik

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    Since a significant amount of redundant information causes problems like inefficiency or congestion in the existing RSS, a method using part of speech (pos) tagging to extract keywords is proposed to solve these problems. Firstly, the title of news is analyzed by using Chinese word segmentation and speech tagging system. Then, the keywords of the title are identified according to their part of speech. All of the extracted keywords are compared, categorized and stored according to the proposed criterion in this paper. In that case, all the news in the same category is identical or similar. Thus, redundant news can be hidden to users. According to the operation, statistics, comparison and analysis of system, and the introduction of the value of P and R and the evaluation parameter, a good redundancy removing result is achieved.

    Original languageEnglish
    Title of host publicationProceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007
    Pages1000-1004
    Number of pages5
    DOIs
    Publication statusPublished - 2007
    Event2007 International Conference on Computational Intelligence and Security, CIS'07 - Harbin, Heilongjiang, China
    Duration: 2007 Dec 152007 Dec 19

    Publication series

    NameProceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007

    Other

    Other2007 International Conference on Computational Intelligence and Security, CIS'07
    Country/TerritoryChina
    CityHarbin, Heilongjiang
    Period07/12/1507/12/19

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computational Theory and Mathematics

    Fingerprint

    Dive into the research topics of 'Speech tagging based improvement of the RSS polymerization news'. Together they form a unique fingerprint.

    Cite this