Retrieval effectiveness of proper name search methods

被引:54
作者
Pfeifer, U
Poersch, T
Fuhr, N
机构
[1] University of Dortmund
关键词
D O I
10.1016/S0306-4573(96)00042-8
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Searching for names, e.g. author names or company names, is still an open problem. This paper reviews known similarity measures. These measures deal with phonetic similarity, typing errors and plain string similarity. It is shown experimentally that all three approaches lead to significantly higher retrieval quality than plain identity. Further improvements are possible by combining different methods; a probabilistic interpretation of string similarity is developed that leads to better results than an ad-hoc approach. Copyright (C) 1996 Elsevier Science Ltd
引用
收藏
页码:667 / 679
页数:13
相关论文
共 16 条
[1]   AUTOMATIC SPELLING CORRECTION USING A TRIGRAM SIMILARITY MEASURE [J].
ANGELL, RC ;
FREUND, GE ;
WILLETT, P .
INFORMATION PROCESSING & MANAGEMENT, 1983, 19 (04) :255-261
[2]  
[Anonymous], 1988, AUTOMATIC TEXT PROCE
[3]  
Buckley Chris, 1985, 85686 CORN U DEP COM
[4]   A TECHNIQUE FOR COMPUTER DETECTION AND CORRECTION OF SPELLING ERRORS [J].
DAMERAU, FJ .
COMMUNICATIONS OF THE ACM, 1964, 7 (03) :171-176
[5]  
FUHR N, 1992, EXPT PRAKTISCHES INF, P59
[6]  
FUHR N, 1990, INFORMATIK UMWELTSCH, P27
[7]   PHONIX - THE ALGORITHM [J].
GADD, TN .
PROGRAM-AUTOMATED LIBRARY AND INFORMATION SYSTEMS, 1990, 24 (04) :363-366
[8]   FISCHING FORE WERDS - PHONETIC RETRIEVAL OF WRITTEN TEXT IN INFORMATION-SYSTEMS [J].
GADD, TN .
PROGRAM-AUTOMATED LIBRARY AND INFORMATION SYSTEMS, 1988, 22 (03) :222-237
[9]   APPROXIMATE STRING MATCHING [J].
HALL, PAV ;
DOWLING, GR .
COMPUTING SURVEYS, 1980, 12 (04) :381-402
[10]  
HARMAN D, 1993, SPECIAL PUBLICATION, P1