{"id":"https://openalex.org/W2024508594","doi":"https://doi.org/10.1145/1458082.1458268","title":"An approximate string matching approach for handling incorrectly typed urls","display_name":"An approximate string matching approach for handling incorrectly typed urls","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2024508594","doi":"https://doi.org/10.1145/1458082.1458268","mag":"2024508594"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082698772","display_name":"Mihai A. Stroe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Mihai Stroe","raw_affiliation_strings":["Google Switzerland GmbH, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google Switzerland GmbH, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011458966","display_name":"Radu Berinde","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radu Berinde","raw_affiliation_strings":["MIT, Cambridge, MA, USA","MIT, Cambridge MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT, Cambridge MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051407242","display_name":"Cosmin Silvestru Negru\u015feri","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cosmin Negruseri","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028699377","display_name":"Dan Popovici","orcid":"https://orcid.org/0000-0003-2534-6828"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Popovici","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA","Google Inc., Mountain View, CA USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082698772"],"corresponding_institution_ids":["https://openalex.org/I4210100430"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10794816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"1339","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7960904836654663},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.7445694804191589},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.7410529851913452},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6868131160736084},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5874131917953491},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.497257262468338},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.4814152717590332},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.4659712314605713},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.45374661684036255},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44317561388015747},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.4389897584915161},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3839166760444641},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3573136627674103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34201329946517944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10487845540046692},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06491082906723022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960904836654663},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7445694804191589},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.7410529851913452},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6868131160736084},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5874131917953491},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.497257262468338},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.4814152717590332},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4659712314605713},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.45374661684036255},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44317561388015747},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.4389897584915161},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3839166760444641},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3573136627674103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34201329946517944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10487845540046692},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06491082906723022},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1854214752","https://openalex.org/W2155512447","https://openalex.org/W6639055396"],"related_works":["https://openalex.org/W2257399947","https://openalex.org/W2371263218","https://openalex.org/W2141423589","https://openalex.org/W2386746909","https://openalex.org/W2399644331","https://openalex.org/W2037600093","https://openalex.org/W2245915510","https://openalex.org/W2366300241","https://openalex.org/W3145288231","https://openalex.org/W2130362787"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"approach":[4],"the":[5,20,49,65],"problem":[6,15],"of":[7,51],"providing":[8],"corrections":[9],"for":[10,44],"incorrectly":[11],"typed":[12],"URLs.":[13,46],"This":[14],"is":[16,60],"significantly":[17],"different":[18],"from":[19],"classical":[21],"spelling":[22],"correction":[23],"problem.":[24],"We":[25,47],"describe":[26],"our":[27,52],"contribution":[28],"-":[29],"building":[30],"a":[31,36],"custom":[32],"data":[33],"structure":[34],"and":[35],"search":[37,67],"algorithm":[38],"that":[39],"can":[40],"find":[41],"approximate":[42],"matches":[43],"incorrect":[45],"evaluate":[48],"quality":[50],"results":[53],"through":[54],"experiments":[55],"with":[56],"analysts.":[57],"Our":[58],"system":[59],"now":[61],"being":[62],"used":[63],"in":[64],"Google":[66],"engine.":[68]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
