{"id":"https://openalex.org/W2090103551","doi":"https://doi.org/10.1145/1645953.1646106","title":"Characteristics of document similarity measures for compliance analysis","display_name":"Characteristics of document similarity measures for compliance analysis","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2090103551","doi":"https://doi.org/10.1145/1645953.1646106","mag":"2090103551"},"language":"en","primary_location":{"id":"doi:10.1145/1645953.1646106","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","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/A5076177223","display_name":"Asad Sayeed","orcid":"https://orcid.org/0000-0002-6839-3926"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asad Sayeed","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108633582","display_name":"Soumitra Sarkar","orcid":"https://orcid.org/0000-0002-4404-2355"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumitra Sarkar","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights,, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights,, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101921697","display_name":"Yu Deng","orcid":"https://orcid.org/0000-0002-7637-0134"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Deng","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights,, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights,, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085326033","display_name":"Rafah Hosn","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafah Hosn","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights,, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights,, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059002634","display_name":"Ruchi Mahindru","orcid":"https://orcid.org/0000-0002-4711-8829"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruchi Mahindru","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights,, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights,, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014550071","display_name":"Nithya Rajamani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nithya Rajamani","raw_affiliation_strings":["IBM Research - India, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - India, Hyderabad, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9748,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75108179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1207","last_page":"1216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9987000226974487,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9987000226974487,"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/T10260","display_name":"Software Engineering Research","score":0.9983000159263611,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/compliance","display_name":"Compliance (psychology)","score":0.6684824228286743},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6253437995910645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5967099666595459},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42910927534103394},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35618945956230164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23125627636909485},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11503911018371582}],"concepts":[{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.6684824228286743},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6253437995910645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5967099666595459},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42910927534103394},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35618945956230164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23125627636909485},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11503911018371582},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1645953.1646106","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1550206324","https://openalex.org/W1568524234","https://openalex.org/W1579572292","https://openalex.org/W1790259861","https://openalex.org/W1986107388","https://openalex.org/W2000273237","https://openalex.org/W2024932032","https://openalex.org/W2032435979","https://openalex.org/W2106571683","https://openalex.org/W2109422812","https://openalex.org/W2118020653","https://openalex.org/W2147152072","https://openalex.org/W2149684865","https://openalex.org/W2505312721","https://openalex.org/W2561675875","https://openalex.org/W3125903889"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2119214692","https://openalex.org/W2115485936","https://openalex.org/W2153015554","https://openalex.org/W2103338134","https://openalex.org/W2349125667"],"abstract_inverted_index":{"Due":[0],"to":[1,36,87,117],"increased":[2],"competition":[3],"in":[4],"the":[5,30,64,94,103,119,140],"IT":[6],"Services":[7],"business,":[8],"improving":[9],"quality,":[10],"reducing":[11],"costs":[12],"and":[13,112],"shortening":[14],"schedules":[15],"has":[16],"become":[17],"extremely":[18],"important.":[19],"A":[20,76],"key":[21],"strategy":[22],"being":[23],"adopted":[24],"for":[25,50,70,92],"achieving":[26],"these":[27],"goals":[28],"is":[29,63,90],"use":[31,65,104],"of":[32,54,60,66,73,96,105,136,138],"an":[33,98],"asset-based":[34],"approach":[35,62],"service":[37,74],"delivery,":[38],"where":[39],"standard":[40,88],"reusable":[41],"components":[42],"developed":[43],"by":[44],"domain":[45],"experts":[46],"are":[47,143],"minimally":[48],"modified":[49],"each":[51,71],"customer":[52],"instead":[53],"creating":[55],"custom":[56],"solutions.":[57],"One":[58],"example":[59],"this":[61],"contract":[67],"templates,":[68],"one":[69],"type":[72],"offered.":[75],"compliance":[77,130],"checking":[78],"system":[79],"that":[80],"measures":[81,108],"how":[82],"well":[83],"actual":[84],"contracts":[85],"adhere":[86],"templates":[89,122],"critical":[91],"ensuring":[93],"success":[95],"such":[97],"approach.":[99],"This":[100],"paper":[101],"describes":[102],"document":[106],"similarity":[107,111],"-":[109,116],"Cosine":[110],"Latent":[113],"Semantic":[114],"Indexing":[115],"identify":[118],"top":[120],"candidate":[121],"on":[123],"which":[124],"a":[125],"more":[126],"detailed":[127],"(and":[128],"expensive)":[129],"analysis":[131],"can":[132],"be":[133],"performed.":[134],"Comparison":[135],"results":[137],"using":[139],"different":[141],"methods":[142],"presented.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}