{"id":"https://openalex.org/W2089119080","doi":"https://doi.org/10.1007/pl00021525","title":"String techniques for detecting duplicates in document databases","display_name":"String techniques for detecting duplicates in document databases","publication_year":2000,"publication_date":"2000-06-01","ids":{"openalex":"https://openalex.org/W2089119080","doi":"https://doi.org/10.1007/pl00021525","mag":"2089119080"},"language":"en","primary_location":{"id":"doi:10.1007/pl00021525","is_oa":false,"landing_page_url":"https://doi.org/10.1007/pl00021525","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition","raw_type":"journal-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/A5088217927","display_name":"Daniel Lopresti","orcid":"https://orcid.org/0000-0003-2129-4223"},"institutions":[{"id":"https://openalex.org/I1322087612","display_name":"Alcatel Lucent (Germany)","ror":"https://ror.org/00c5mwp75","country_code":"DE","type":"company","lineage":["https://openalex.org/I1322087612"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniel P. Lopresti","raw_affiliation_strings":["Bell Laboratories, Lucent Technologies, Inc., 600 Mountain Avenue, Room 2D-447, Murray Hill, NJ 07974, USA; e-mail: dpl@research.bell-labs.com\n, , , , , , US","Bell Laboratories, Lucent Technologies, Inc., 600 Mountain Avenue, Room 2D-447, Murray Hill, NJ 07974, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bell Laboratories, Lucent Technologies, Inc., 600 Mountain Avenue, Room 2D-447, Murray Hill, NJ 07974, USA; e-mail: dpl@research.bell-labs.com\n, , , , , , US","institution_ids":["https://openalex.org/I1322087612"]},{"raw_affiliation_string":"Bell Laboratories, Lucent Technologies, Inc., 600 Mountain Avenue, Room 2D-447, Murray Hill, NJ 07974, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088217927"],"corresponding_institution_ids":["https://openalex.org/I1322087612"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":2.2406,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90032226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":"4","first_page":"186","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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/T11719","display_name":"Data Quality and Management","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.857185959815979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7717815041542053},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6876394152641296},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6182403564453125},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5894272327423096},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5516449809074402},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4956732988357544},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4398655295372009},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.42960605025291443},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.4289669990539551},{"id":"https://openalex.org/keywords/realm","display_name":"Realm","score":0.41513410210609436},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40154799818992615},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38080528378486633},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3549608588218689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2966952919960022},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.26797741651535034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10370045900344849},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1021682620048523}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.857185959815979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717815041542053},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6876394152641296},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6182403564453125},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5894272327423096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5516449809074402},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4956732988357544},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4398655295372009},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.42960605025291443},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4289669990539551},{"id":"https://openalex.org/C2778757428","wikidata":"https://www.wikidata.org/wiki/Q1250464","display_name":"Realm","level":2,"score":0.41513410210609436},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40154799818992615},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38080528378486633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3549608588218689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2966952919960022},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.26797741651535034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10370045900344849},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1021682620048523},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/pl00021525","is_oa":false,"landing_page_url":"https://doi.org/10.1007/pl00021525","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1501400124","https://openalex.org/W1529615245","https://openalex.org/W1596691921","https://openalex.org/W1647671624","https://openalex.org/W1860104593","https://openalex.org/W1941707302","https://openalex.org/W1970026646","https://openalex.org/W1974926861","https://openalex.org/W1979547397","https://openalex.org/W1990413869","https://openalex.org/W2020532774","https://openalex.org/W2057989089","https://openalex.org/W2061996139","https://openalex.org/W2063743738","https://openalex.org/W2072054026","https://openalex.org/W2074231493","https://openalex.org/W2088179629","https://openalex.org/W2097284241","https://openalex.org/W2135950423","https://openalex.org/W2160043573","https://openalex.org/W2257399947","https://openalex.org/W2610179052","https://openalex.org/W3098786064"],"related_works":["https://openalex.org/W2054173104","https://openalex.org/W2257399947","https://openalex.org/W2051764263","https://openalex.org/W2935705348","https://openalex.org/W2069035364","https://openalex.org/W2358632292","https://openalex.org/W2111239386","https://openalex.org/W52396946","https://openalex.org/W4200287105","https://openalex.org/W2187092961"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}