{"id":"https://openalex.org/W1973846693","doi":"https://doi.org/10.1145/2433396.2433486","title":"Maguro, a system for indexing and searching over very large text collections","display_name":"Maguro, a system for indexing and searching over very large text collections","publication_year":2013,"publication_date":"2013-02-04","ids":{"openalex":"https://openalex.org/W1973846693","doi":"https://doi.org/10.1145/2433396.2433486","mag":"1973846693"},"language":"en","primary_location":{"id":"doi:10.1145/2433396.2433486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2433396.2433486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth ACM international conference on Web search 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/A5083087030","display_name":"Knut Magne Risvik","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210135422","display_name":"Microsoft (Norway)","ror":"https://ror.org/03jtz4s80","country_code":"NO","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210135422"]}],"countries":["NO","US"],"is_corresponding":false,"raw_author_name":"Knut Magne Risvik","raw_affiliation_strings":["Microsoft, Oslo, Norway","Microsoft, Oslo, Norway#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Oslo, Norway","institution_ids":["https://openalex.org/I4210135422"]},{"raw_affiliation_string":"Microsoft, Oslo, Norway#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013670321","display_name":"Trishul Chilimbi","orcid":"https://orcid.org/0000-0001-6711-1117"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trishul Chilimbi","raw_affiliation_strings":["Microsoft, Redmond, USA","Microsoft Redmond, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111780030","display_name":"Henry Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Tan","raw_affiliation_strings":["Microsoft, Redmond, USA","Microsoft Redmond, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061445851","display_name":"Karthik Kalyanaraman","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Kalyanaraman","raw_affiliation_strings":["Microsoft, Redmond, USA","Microsoft Redmond, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063602816","display_name":"Chris Anderson","orcid":"https://orcid.org/0000-0001-9573-141X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Anderson","raw_affiliation_strings":["Microsoft, Redmond, USA","Microsoft Redmond, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"727","last_page":"736"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9970999956130981,"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/metadata","display_name":"Metadata","score":0.9069160223007202},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8255754709243774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622731924057007},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6657692790031433},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6283437013626099},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5127297639846802},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46619242429733276},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42233967781066895},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3642292618751526},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08977404236793518}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9069160223007202},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8255754709243774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622731924057007},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6657692790031433},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6283437013626099},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5127297639846802},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46619242429733276},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42233967781066895},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3642292618751526},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08977404236793518}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2433396.2433486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2433396.2433486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1503312990","https://openalex.org/W1515087027","https://openalex.org/W1532325895","https://openalex.org/W1660390307","https://openalex.org/W2001276096","https://openalex.org/W2054503816","https://openalex.org/W2055176966","https://openalex.org/W2063435439","https://openalex.org/W2066500746","https://openalex.org/W2069870183","https://openalex.org/W2073965851","https://openalex.org/W2100830825","https://openalex.org/W2101768888","https://openalex.org/W2119400430","https://openalex.org/W2134337235","https://openalex.org/W2147028271","https://openalex.org/W2154610494","https://openalex.org/W2164619507","https://openalex.org/W2364964713","https://openalex.org/W2407789994","https://openalex.org/W3003506064","https://openalex.org/W6637101025"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W4282568653","https://openalex.org/W2119380317","https://openalex.org/W2070155952","https://openalex.org/W2082868123"],"abstract_inverted_index":{"Maguro":[0,65,85],"is":[1,28,66,86],"a":[2],"system":[3],"for":[4,50,57,68],"efficiently":[5],"searching":[6],"very":[7,29,81],"large":[8],"collections":[9],"of":[10,13,40,47,72,88],"text":[11],"content":[12,26,39,48,73],"up":[14],"to":[15,36,97],"1":[16],"trillion":[17],"documents":[18],"at":[19],"low":[20],"cost.":[21],"Search":[22],"engines":[23],"span":[24],"across":[25,60],"that":[27],"dynamic":[30],"and":[31,77,94],"highly":[32],"augmented":[33],"with":[34,74],"metadata":[35],"the":[37,41,54,61,69,89,99],"tail":[38,45,71],"web.":[42],"A":[43],"long":[44,70],"distribution":[46],"calls":[49],"different":[51],"trade-offs":[52],"in":[53,92],"design":[55],"space":[56],"good":[58,82],"efficiency":[59],"entire":[62],"index":[63,100],"range.":[64],"designed":[67],"less":[75,78],"dynamics":[76],"metadata,":[79],"but":[80],"cost":[83],"efficiency.":[84],"part":[87],"serving":[90],"stack":[91],"Bing":[93],"allows":[95],"us":[96],"scale":[98],"significantly":[101],"better.":[102]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}