{"id":"https://openalex.org/W1985895460","doi":"https://doi.org/10.1145/1008992.1009131","title":"Constructing a text corpus for inexact duplicate detection","display_name":"Constructing a text corpus for inexact duplicate detection","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W1985895460","doi":"https://doi.org/10.1145/1008992.1009131","mag":"1985895460"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5025701458","display_name":"Jack G. Conrad","orcid":"https://orcid.org/0000-0001-9114-9385"},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jack G. Conrad","raw_affiliation_strings":["Thomson Legal &amp; Regulatory, St. Paul, MN"],"affiliations":[{"raw_affiliation_string":"Thomson Legal &amp; Regulatory, St. Paul, MN","institution_ids":["https://openalex.org/I68384125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001552911","display_name":"Cindy P. Schriber","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cindy P. Schriber","raw_affiliation_strings":["Thomson--West, St. Paul, MN"],"affiliations":[{"raw_affiliation_string":"Thomson--West, St. Paul, MN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025701458"],"corresponding_institution_ids":["https://openalex.org/I68384125"],"apc_list":null,"apc_paid":null,"fwci":2.3672,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90945046,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9969000220298767,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.817900538444519},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6170032024383545},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5147571563720703},{"id":"https://openalex.org/keywords/phenomenon","display_name":"Phenomenon","score":0.48473355174064636},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4593439996242523},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38978537917137146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817900538444519},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6170032024383545},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5147571563720703},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.48473355174064636},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4593439996242523},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38978537917137146},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1008992.1009131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1536700701","https://openalex.org/W1941707302","https://openalex.org/W2067432306","https://openalex.org/W2093583221","https://openalex.org/W2111549955","https://openalex.org/W2152565070","https://openalex.org/W2153804780","https://openalex.org/W2998461326"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4300450609","https://openalex.org/W4386931570","https://openalex.org/W2391010541","https://openalex.org/W2357367123","https://openalex.org/W4388930439","https://openalex.org/W2387276901","https://openalex.org/W2385953334","https://openalex.org/W2351303360","https://openalex.org/W3134118520"],"abstract_inverted_index":{"As":[0],"online":[1],"document":[2],"collections":[3],"continue":[4],"to":[5,29,43,64],"expand,":[6],"both":[7,55],"on":[8,48],"the":[9,15,34,52],"Web":[10],"and":[11,39,57,71],"in":[12],"proprietary":[13],"environments,":[14],"need":[16],"for":[17,69],"duplicate":[18,74],"detection":[19],"becomes":[20],"more":[21],"critical.":[22],"The":[23],"goal":[24],"of":[25,36,54],"this":[26],"work":[27],"is":[28],"facilitate":[30],"(a)":[31],"investigations":[32],"into":[33],"phenomenon":[35],"near":[37],"duplicates":[38],"(b)":[40],"algorithmic":[41],"approaches":[42],"minimizing":[44],"its":[45],"negative":[46],"effect":[47],"search":[49],"results.":[50],"Harnessing":[51],"expertise":[53],"client-users":[56],"professional":[58],"searchers,":[59],"we":[60],"establish":[61],"principled":[62],"methods":[63],"generate":[65],"a":[66],"test":[67],"collection":[68],"identifying":[70],"handling":[72],"inexact":[73],"documents.":[75]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
