{"id":"https://openalex.org/W2032866865","doi":"https://doi.org/10.1145/1498759.1498761","title":"Challenges in building large-scale information retrieval systems","display_name":"Challenges in building large-scale information retrieval systems","publication_year":2009,"publication_date":"2009-02-09","ids":{"openalex":"https://openalex.org/W2032866865","doi":"https://doi.org/10.1145/1498759.1498761","mag":"2032866865"},"language":"en","primary_location":{"id":"doi:10.1145/1498759.1498761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","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/A5043872671","display_name":"Jay B. Dean","orcid":"https://orcid.org/0000-0003-1362-0500"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeffrey Dean","raw_affiliation_strings":["Google, Inc","GOOGLE INC "],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043872671"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":39.6721,"has_fulltext":false,"cited_by_count":192,"citation_normalized_percentile":{"value":0.99718119,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9764999747276306,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9764999747276306,"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":0.947700023651123,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9368000030517578,"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":0.8235651254653931},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.575177013874054},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5598781108856201},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5232205390930176},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4592236876487732},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33274900913238525},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3238828182220459},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11087372899055481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235651254653931},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.575177013874054},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5598781108856201},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5232205390930176},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4592236876487732},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33274900913238525},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3238828182220459},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11087372899055481},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1498759.1498761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2118564381","https://openalex.org/W2163901716","https://openalex.org/W2152204162","https://openalex.org/W2739821120","https://openalex.org/W2150136235","https://openalex.org/W2026095310","https://openalex.org/W2140661912","https://openalex.org/W2056806613","https://openalex.org/W2153069032"],"abstract_inverted_index":{"Building":[0],"and":[1,49,59,70,82,86,109,113,154],"operating":[2],"large-scale":[3],"information":[4,110],"retrieval":[5,111,145],"systems":[6,25,112,140],"used":[7,94],"by":[8],"hundreds":[9],"of":[10,12,20,34,40,61,88,105,115,126,138],"millions":[11],"people":[13],"around":[14],"the":[15,38,50,57,68,80,84,89,103,116],"world":[16],"provides":[17],"a":[18,32],"number":[19,33,39,58],"interesting":[21],"challenges.":[22],"Designing":[23],"such":[24],"requires":[26],"making":[27],"complex":[28],"design":[29,117],"tradeoffs":[30],"in":[31,124,158],"dimensions,":[35],"including":[36],"(a)":[37],"user":[41],"queries":[42],"that":[43,64,92,119],"must":[44],"be":[45],"handled":[46],"per":[47],"second":[48],"response":[51],"latency":[52,69],"to":[53,79],"these":[54,127,144],"requests,":[55],"(b)":[56],"size":[60],"various":[62,136],"corpora":[63],"are":[65,75,93],"searched,":[66],"(c)":[67],"frequency":[71],"with":[72],"which":[73],"documents":[74],"updated":[76],"or":[77],"added":[78],"corpora,":[81],"(d)":[83],"quality":[85],"cost":[87],"ranking":[90],"algorithms":[91],"for":[95],"retrieval.":[96],"In":[97],"this":[98,159],"talk":[99],"I":[100,129,148],"will":[101,130,149],"discuss":[102],"evolution":[104],"Google's":[106],"hardware":[107],"infrastructure":[108,141],"some":[114,151],"challenges":[118,153],"arise":[120],"from":[121],"ever-increasing":[122],"demands":[123],"all":[125],"dimensions.":[128],"also":[131],"describe":[132,150],"how":[133],"we":[134],"use":[135],"pieces":[137],"distributed":[139],"when":[142],"building":[143],"systems.":[146],"Finally,":[147],"future":[152],"open":[155],"research":[156],"problems":[157],"area.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":16}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
