摘要
Thispaperpresentsanewwaytoextractconceptthatcanbeusedtoimprovetextclassificationper-formance(precisionandrecall).Thecomputationalmeasurewillbedividedintotwolayers.Thebottomlayercalleddocumentlayerisconcernedwithextractingtheconceptsofparti-culardocumentandtheupperlayercalledcategorylayeriswithfindingthedescriptionandsubjectconceptsofparticularcategory.Therelevantim-plementationalgorithmthatdramatic-allydecreasesthesearchspaceisdis-cussedindetail.Theexperimentbasedonreal-worlddatacollectedfromInfo-Bankshowsthattheapproachissupe-riortothetraditionalones.
出版日期
2003年04月14日(中国期刊网平台首次上网日期,不代表论文的发表时间)