?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Fast+phonetic+similarity+search+over+large+repositories&rft.creator=Tissot%2C+H&rft.creator=Peschl%2C+G&rft.creator=Del+Fabro%2C+MD&rft.description=Analysis+of+unstructured+data+may+be+inefficient+in+the+presence+of+spelling+errors.+Existing+approaches+use+string+similarity+methods+to+search+for+valid+words+within+a+text%2C+with+a+supporting+dictionary.+However%2C+they+are+not+rich+enough+to+encode+phonetic+information+to+assist+the+search.+In+this+paper%2C+we+present+a+novel+approach+for+efficiently+perform+phonetic+similarity+search+over+large+data+sources%2C+that+uses+a+data+structure+called+PhoneticMap+to+encode+language-specific+phonetic+information.+We+validate+our+approach+through+an+experiment+over+a+data+set+using+a+Portuguese+variant+of+a+well-known+repository%2C+to+automatically+correct+words+with+spelling+errors.&rft.subject=Phonetic+Similarity%2C+String+Similarity%2C+Fast+Search&rft.publisher=Springer&rft.date=2014-01-01&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Database+and+Expert+Systems+Applications.++(pp.+pp.+74-81).++Springer%3A+Cham%2C+Switzerland.+(2014)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10065716%2F1%2FDEXA-2014-FPSS.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10065716%2F&rft.rights=open