{"id":"https://openalex.org/W2003108016","doi":"https://doi.org/10.1145/1557019.1557137","title":"Applying syntactic similarity algorithms for enterprise information management","display_name":"Applying syntactic similarity algorithms for enterprise information management","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2003108016","doi":"https://doi.org/10.1145/1557019.1557137","mag":"2003108016"},"language":"en","primary_location":{"id":"doi:10.1145/1557019.1557137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016669578","display_name":"Ludmila Cherkasova","orcid":"https://orcid.org/0000-0002-9333-4901"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludmila Cherkasova","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088426443","display_name":"Kave Eshghi","orcid":"https://orcid.org/0000-0003-3374-3145"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kave Eshghi","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090701350","display_name":"Charles B. Morrey","orcid":"https://orcid.org/0009-0009-4334-6275"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles B. Morrey","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023021993","display_name":"Joseph Tucek","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Tucek","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083350972","display_name":"Alistair Veitch","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alistair Veitch","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1087","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/T11719","display_name":"Data Quality and Management","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8252875804901123},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6026611924171448},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5864416360855103},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5341642498970032},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5000560283660889},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48858723044395447},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46101513504981995},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36308854818344116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2922132909297943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2840619385242462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252875804901123},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6026611924171448},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5864416360855103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5341642498970032},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5000560283660889},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48858723044395447},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46101513504981995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36308854818344116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2922132909297943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2840619385242462},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1557019.1557137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.295.7716","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.295.7716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/personal/Lucy_Cherkasova/papers/lc556-cherkasova-colored.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W137089333","https://openalex.org/W318559539","https://openalex.org/W841409518","https://openalex.org/W1536700701","https://openalex.org/W1609518033","https://openalex.org/W1941707302","https://openalex.org/W1991800036","https://openalex.org/W1997657677","https://openalex.org/W2007842132","https://openalex.org/W2012833704","https://openalex.org/W2056980397","https://openalex.org/W2067432306","https://openalex.org/W2081193615","https://openalex.org/W2085922539","https://openalex.org/W2123767107","https://openalex.org/W2128272588","https://openalex.org/W2132069633","https://openalex.org/W2152565070","https://openalex.org/W2164634022","https://openalex.org/W6611141452","https://openalex.org/W6636190696","https://openalex.org/W6679663036","https://openalex.org/W6682678078"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W1926736923","https://openalex.org/W2942177010"],"abstract_inverted_index":{"For":[0,67],"implementing":[1],"content":[2,31],"management":[3],"solutions":[4],"and":[5,15,34,115,132],"enabling":[6],"new":[7],"applications":[8],"associated":[9],"with":[10,85],"data":[11],"retention,":[12],"regulatory":[13],"compliance,":[14],"litigation":[16],"issues,":[17],"enterprises":[18],"need":[19],"to":[20,24,106,152],"develop":[21],"advanced":[22],"analytics":[23],"uncover":[25],"relationships":[26],"among":[27],"the":[28,41,57,96,109,134,137],"documents,":[29],"e.g.,":[30],"similarity,":[32],"provenance,":[33],"clustering.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,70],"evaluate":[40],"performance":[42,92,135],"of":[43,76,82,89,99,108,124,136,159],"four":[44,101,138],"syntactic":[45],"similarity":[46,97],"algorithms.":[47],"Three":[48],"algorithms":[49,102,139,151],"are":[50],"based":[51],"on":[52],"Broder's":[53],"\"shingling\"":[54],"technique":[55],"while":[56],"fourth":[58],"algorithm":[59],"employs":[60],"a":[61,72,80,86,121,141],"more":[62],"recent":[63],"approach,":[64],"\"content-based":[65],"chunking\".":[66],"our":[68,146],"experiments,":[69],"use":[71],"specially":[73],"designed":[74],"corpus":[75],"documents":[77,84],"that":[78,95],"includes":[79],"set":[81],"\"similar\"":[83],"controlled":[87,142],"number":[88],"modifications.":[90],"Our":[91],"study":[93],"reveals":[94],"metric":[98],"all":[100],"is":[103],"highly":[104],"sensitive":[105],"settings":[107],"algorithms'":[110],"parameters:":[111],"sliding":[112],"window":[113],"size":[114],"fingerprint":[116],"sampling":[117],"frequency.":[118],"We":[119,144],"identify":[120],"useful":[122],"range":[123],"these":[125,150],"parameters":[126],"for":[127],"achieving":[128],"good":[129],"practical":[130],"results,":[131],"compare":[133],"in":[140,155],"environment.":[143],"validate":[145],"results":[147],"by":[148],"applying":[149],"finding":[153],"near-duplicates":[154],"two":[156],"large":[157],"collections":[158],"HP":[160],"technical":[161],"support":[162],"documents.":[163]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}