{"id":"https://openalex.org/W2060636190","doi":"https://doi.org/10.1145/1645953.1646043","title":"Automatic retrieval of similar content using search engine query interface","display_name":"Automatic retrieval of similar content using search engine query interface","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2060636190","doi":"https://doi.org/10.1145/1645953.1646043","mag":"2060636190"},"language":"en","primary_location":{"id":"doi:10.1145/1645953.1646043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646043","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":"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/A5043774457","display_name":"Ali Dasdan","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ali Dasdan","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA, USA","Yahoo, Inc., Sunnyvale, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052262436","display_name":"Paolo D\u2019Alberto","orcid":"https://orcid.org/0000-0002-1584-1270"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Paolo D'Alberto","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA, USA","Yahoo, Inc., Sunnyvale, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050340255","display_name":"Santanu Kolay","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Santanu Kolay","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA, USA","Yahoo, Inc., Sunnyvale, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008836671","display_name":"Chris Drome","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Chris Drome","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA, USA","Yahoo, Inc., Sunnyvale, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1708,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92118164,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"701","last_page":"710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8552422523498535},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7583006024360657},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.7451505064964294},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6628574132919312},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6252481937408447},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.6162226796150208},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6033506393432617},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.570558488368988},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5544530153274536},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.5390083193778992},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.47858524322509766},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4702029824256897},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4397372603416443},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.4248826503753662},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34913498163223267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23997756838798523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552422523498535},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7583006024360657},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.7451505064964294},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6628574132919312},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6252481937408447},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.6162226796150208},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6033506393432617},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.570558488368988},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5544530153274536},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.5390083193778992},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.47858524322509766},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4702029824256897},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4397372603416443},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.4248826503753662},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34913498163223267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23997756838798523},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1645953.1646043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646043","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.7154","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.7154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mashup.pubs.dbs.uni-leipzig.de/files/Automatic_retrieval_of_similar_content_using_search_engine_query_interface.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332434","display_name":"ExxonMobil Research and Engineering Company","ror":"https://ror.org/01xcepn55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W197093853","https://openalex.org/W1596691921","https://openalex.org/W1605217017","https://openalex.org/W1614703486","https://openalex.org/W1974339500","https://openalex.org/W1985697096","https://openalex.org/W1989856433","https://openalex.org/W1991240715","https://openalex.org/W1991800036","https://openalex.org/W1997657677","https://openalex.org/W2007842132","https://openalex.org/W2012833704","https://openalex.org/W2069870183","https://openalex.org/W2072582979","https://openalex.org/W2085922539","https://openalex.org/W2092246763","https://openalex.org/W2108636652","https://openalex.org/W2109664771","https://openalex.org/W2111593814","https://openalex.org/W2132069633","https://openalex.org/W2143450461","https://openalex.org/W2145349611","https://openalex.org/W2148885851","https://openalex.org/W2152565070","https://openalex.org/W2154707336","https://openalex.org/W2209091593","https://openalex.org/W2295428206","https://openalex.org/W6607922304","https://openalex.org/W6661517966","https://openalex.org/W6676373471","https://openalex.org/W6679663036"],"related_works":["https://openalex.org/W2901901036","https://openalex.org/W2013069866","https://openalex.org/W2350026801","https://openalex.org/W8514837","https://openalex.org/W227397245","https://openalex.org/W2181886559","https://openalex.org/W2363027842","https://openalex.org/W2259159363","https://openalex.org/W2106022318","https://openalex.org/W2402674558"],"abstract_inverted_index":{"We":[0,88,100],"consider":[1],"the":[2,25,31,62,65,68,73,78,81,85,95],"coverage":[3,42],"testing":[4],"problem":[5,34],"where":[6],"we":[7,48],"are":[8,124],"given":[9],"a":[10,13,16,28,58],"document":[11,83],"and":[12,20,71,76,84,93,105,117],"corpus":[14,26,66],"with":[15],"limited":[17],"query":[18,59,64,69],"interface":[19],"asked":[21],"to":[22,91],"find":[23],"if":[24],"contains":[27],"near-duplicate":[29],"of":[30,97],"document.":[32],"This":[33],"has":[35],"applications":[36],"in":[37,53,119],"search":[38,114],"engines":[39],"for":[40],"competitive":[41],"testing.":[43],"To":[44],"solve":[45],"this":[46],"problem,":[47],"propose":[49],"approaches":[50],"that":[51,107],"work":[52],"three":[54],"main":[55],"steps:":[56],"generate":[57],"signature":[60,70],"from":[61],"document,":[63],"using":[67],"scrape":[72],"returned":[74,86],"results,":[75],"validate":[77],"similarity":[79],"between":[80],"input":[82],"results.":[87],"discuss":[89],"techniques":[90],"control":[92],"bound":[94],"performance":[96,127],"these":[98,108],"methods.":[99],"perform":[101,110],"large-scale":[102],"experimental":[103],"validation":[104],"show":[106],"methods":[109],"well":[111],"across":[112],"different":[113],"engine":[115],"corpora":[116],"documents":[118],"multiple":[120],"languages.":[121],"They":[122],"also":[123],"robust":[125],"against":[126],"parameter":[128],"variations.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
