Approximate personal name-matching through finite-state graphs Export

@article{galvez07approximate, abstract = {This article shows how finite-state methods can be employed in a new and different task: the conflation of personal name variants in standard forms. In bibliographic databases and citation index systems, variant forms create problems of inaccuracy that affect information retrieval, the quality of information from databases, and the citation statistics used for the evaluation of scientists' work. A number of approximate string matching techniques have been developed to validate variant forms, based on similarity and equivalence relations. We classify the personal name variants as nonvalid and valid forms. In establishing an equivalence relation between valid variants and the standard form of its equivalence class, we defend the application of finite-state transducers. The process of variant identification requires the elaboration of: (a) binary matrices and (b) finite-state graphs. This procedure was tested on samples of author names from bibliographic records, selected from the Library and Information Science Abstracts and Science Citation Index Expanded databases. The evaluation involved calculating the measures of precision and recall, based on completeness and accuracy. The results demonstrate the usefulness of this approach, although it should be complemented with methods based on similarity relations for the recognition of spelling variants and misspellings.}, address = {Department of information Science, University of Granada, Campus Cartuja, Colegio M\'{a}ximo, 18071 Granada, Spain}, author = {Galvez, Carmen and Moya-Aneg\'{o}n, F\'{e}lix}, citeulike-article-id = {5490120}, citeulike-linkout-0 = {http://dx.doi.org/10.1002/asi.20671}, citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/116329764/ABSTRACT}, doi = {10.1002/asi.20671}, issn = {1532-2890}, journal = {Journal of the American Society for Information Science and Technology}, keywords = {evaluation, precision, recall}, number = {13}, pages = {1960--1976}, posted-at = {2009-08-20 15:34:51}, priority = {0}, title = {Approximate personal name-matching through finite-state graphs}, url = {http://dx.doi.org/10.1002/asi.20671}, volume = {58}, year = {2007} }

TY - JOUR ID - galvez07approximate L3 - citeulike-article-id:5490120 N2 - This article shows how finite-state methods can be employed in a new and different task: the conflation of personal name variants in standard forms. In bibliographic databases and citation index systems, variant forms create problems of inaccuracy that affect information retrieval, the quality of information from databases, and the citation statistics used for the evaluation of scientists' work. A number of approximate string matching techniques have been developed to validate variant forms, based on similarity and equivalence relations. We classify the personal name variants as nonvalid and valid forms. In establishing an equivalence relation between valid variants and the standard form of its equivalence class, we defend the application of finite-state transducers. The process of variant identification requires the elaboration of: (a) binary matrices and (b) finite-state graphs. This procedure was tested on samples of author names from bibliographic records, selected from the Library and Information Science Abstracts and Science Citation Index Expanded databases. The evaluation involved calculating the measures of precision and recall, based on completeness and accuracy. The results demonstrate the usefulness of this approach, although it should be complemented with methods based on similarity relations for the recognition of spelling variants and misspellings. IS - 13 JF - Journal of the American Society for Information Science and Technology SN - 1532-2890 AD - Department of information Science, University of Granada, Campus Cartuja, Colegio Máximo, 18071 Granada, Spain EP - 1976 TI - Approximate personal name-matching through finite-state graphs VL - 58 SP - 1960 KW - evaluation KW - precision KW - recall AU - Galvez, Carmen AU - Moya-Anegón, Félix PY - 2007/// UR - http://dx.doi.org/10.1002/asi.20671 ER -