{"id":"https://openalex.org/W2052253513","doi":"https://doi.org/10.1145/1146598.1146663","title":"Next steps in near-duplicate detection for eRulemaking","display_name":"Next steps in near-duplicate detection for eRulemaking","publication_year":2006,"publication_date":"2006-05-21","ids":{"openalex":"https://openalex.org/W2052253513","doi":"https://doi.org/10.1145/1146598.1146663","mag":"2052253513"},"language":"en","primary_location":{"id":"doi:10.1145/1146598.1146663","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146598.1146663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 international conference on Digital government research","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/A5102868374","display_name":"Hui Yang","orcid":"https://orcid.org/0009-0004-4717-2042"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Yang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091813158","display_name":"Stuart W. Shulman","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stuart Shulman","raw_affiliation_strings":["University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102868374"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":6.9927,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96814998,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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/metadata","display_name":"Metadata","score":0.7970199584960938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7843852043151855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.592484712600708},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5531156659126282},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.501798152923584},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4958969056606293},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45964598655700684},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4071338176727295},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35590171813964844}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7970199584960938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843852043151855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.592484712600708},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5531156659126282},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.501798152923584},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4958969056606293},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45964598655700684},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4071338176727295},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35590171813964844},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1146598.1146663","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146598.1146663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 international conference on Digital government research","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.3732","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.3732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~huiyang/publication/dgo2006-yang.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.8833","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.8833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~callan/Papers/dgo06-huiyang.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.3692","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.3692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://erulemaking.ucsur.pitt.edu/doc/papers/dgo_2006_ver23.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W143832144","https://openalex.org/W1499061355","https://openalex.org/W1506964942","https://openalex.org/W1509080340","https://openalex.org/W1575770195","https://openalex.org/W1596691921","https://openalex.org/W1609518033","https://openalex.org/W1994748209","https://openalex.org/W2007842132","https://openalex.org/W2044434631","https://openalex.org/W2053154970","https://openalex.org/W2067432306","https://openalex.org/W2111549955","https://openalex.org/W2115657355","https://openalex.org/W2136542423","https://openalex.org/W2152565070","https://openalex.org/W2164634022","https://openalex.org/W2309001609","https://openalex.org/W3124554374","https://openalex.org/W4240913316","https://openalex.org/W4247903245","https://openalex.org/W4288912538"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2768810474","https://openalex.org/W599624254"],"abstract_inverted_index":{"Large":[0],"volume":[1],"public":[2,11,117],"comment":[3,118],"campaigns":[4],"and":[5,23,55,58,73,104,112],"web":[6],"portals":[7],"that":[8,37,45,123],"encourage":[9],"the":[10],"to":[12,49,108,138],"customize":[13],"form":[14,38,110],"letters":[15,111],"produce":[16],"many":[17],"near-duplicate":[18,56,64,91,140],"documents,":[19,65],"which":[20],"increases":[21],"processing":[22],"storage":[24],"costs,":[25],"but":[26],"is":[27,36,66,125],"rarely":[28],"a":[29,86,89,96],"serious":[30,34],"problem.":[31],"A":[32],"more":[33],"concern":[35],"letter":[39],"customizations":[40],"can":[41],"include":[42],"substantive":[43],"issues":[44],"agencies":[46],"are":[47],"likely":[48],"overlook.":[50],"The":[51,132],"identification":[52],"of":[53,60,70,88],"exact-":[54],"texts,":[57],"recognition":[59],"unique":[61],"text":[62],"within":[63],"an":[67],"important":[68],"component":[69],"data":[71],"cleaning":[72],"integration":[74],"processes":[75],"for":[76],"eRulemaking.This":[77],"paper":[78,133],"presents":[79],"DURIAN":[80,94,124],"(DUplicate":[81],"Removal":[82],"In":[83],"lArge":[84],"collectioN),":[85],"refinement":[87],"prior":[90],"detection":[92,141],"algorithm":[93],"uses":[95],"traditional":[97],"bag-of-words":[98],"document":[99,101,105],"representation,":[100],"attributes":[102],"(\"metadata\"),":[103],"content":[106],"structure":[107],"identify":[109],"their":[113],"edited":[114],"copies":[115],"in":[116],"collections.":[119],"Experimental":[120],"results":[121],"demonstrate":[122],"about":[126],"as":[127,129],"effective":[128],"human":[130],"assessors.":[131],"concludes":[134],"by":[135],"discussing":[136],"challenges":[137],"moving":[139],"into":[142],"operational":[143],"rulemaking":[144],"environments.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
