{"id":"https://openalex.org/W2145185686","doi":"https://doi.org/10.1145/1935826.1935907","title":"Document assignment in multi-site search engines","display_name":"Document assignment in multi-site search engines","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2145185686","doi":"https://doi.org/10.1145/1935826.1935907","mag":"2145185686"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth 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/A5049583553","display_name":"Ulf Brefeld","orcid":"https://orcid.org/0000-0001-9600-6463"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ulf Brefeld","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015615642","display_name":"B. Barla Cambazo\u011flu","orcid":"https://orcid.org/0000-0003-2192-3819"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"B. Barla Cambazoglu","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039618797","display_name":"Flavio Junqueira","orcid":"https://orcid.org/0009-0000-6789-5505"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Flavio P. Junqueira","raw_affiliation_strings":["Yahoo! Research, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049583553"],"corresponding_institution_ids":["https://openalex.org/I2800095910"],"apc_list":null,"apc_paid":null,"fwci":3.6948,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94024875,"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":"575","last_page":"584"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9968000054359436,"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":0.8571170568466187},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7474355697631836},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7046589255332947},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6712132096290588},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5717163681983948},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5645788908004761},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.49620896577835083},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49493831396102905},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4645054042339325},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.4432372450828552},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.41172075271606445},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3860582113265991},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3622850179672241},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35656851530075073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571170568466187},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7474355697631836},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7046589255332947},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6712132096290588},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5717163681983948},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5645788908004761},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.49620896577835083},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49493831396102905},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4645054042339325},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.4432372450828552},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.41172075271606445},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3860582113265991},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3622850179672241},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35656851530075073},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1935826.1935907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W15020643","https://openalex.org/W62563893","https://openalex.org/W140310380","https://openalex.org/W183066880","https://openalex.org/W232533489","https://openalex.org/W1482260847","https://openalex.org/W1488690452","https://openalex.org/W1528262008","https://openalex.org/W1536816303","https://openalex.org/W1780185704","https://openalex.org/W1973030322","https://openalex.org/W1983078185","https://openalex.org/W2002682102","https://openalex.org/W2005422315","https://openalex.org/W2006111471","https://openalex.org/W2028083097","https://openalex.org/W2030649419","https://openalex.org/W2035720976","https://openalex.org/W2039678943","https://openalex.org/W2062444395","https://openalex.org/W2073965851","https://openalex.org/W2082973176","https://openalex.org/W2086253379","https://openalex.org/W2104588805","https://openalex.org/W2106310992","https://openalex.org/W2110653985","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2119821739","https://openalex.org/W2122166301","https://openalex.org/W2125993116","https://openalex.org/W2129191766","https://openalex.org/W2131149563","https://openalex.org/W2135764309","https://openalex.org/W2140534173","https://openalex.org/W2142623206","https://openalex.org/W2143079043","https://openalex.org/W2148103387","https://openalex.org/W2149684865","https://openalex.org/W2154045882","https://openalex.org/W2172142456","https://openalex.org/W2914484678","https://openalex.org/W4255459561","https://openalex.org/W6608994054"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W2095543197","https://openalex.org/W2371838993","https://openalex.org/W1770021664","https://openalex.org/W33687805","https://openalex.org/W2406286368"],"abstract_inverted_index":{"Assigning":[0],"documents":[1,21,30,162,167],"accurately":[2],"to":[3,27,38,68,110,140,148,164],"sites":[4,18],"is":[5],"critical":[6],"for":[7],"the":[8,60,74,112],"performance":[9,75,136],"of":[10,62,76,98,161],"multi-site":[11],"Web":[12,42,87],"search":[13,66,99],"engines.":[14],"In":[15,48],"such":[16,122],"settings,":[17],"crawl":[19],"only":[20],"they":[22],"index":[23],"and":[24,106,125,129],"forward":[25],"queries":[26],"obtain":[28,149],"best-matching":[29],"from":[31,84,95],"other":[32],"sites.":[33,170],"Inaccurate":[34],"assignments":[35],"may":[36],"lead":[37],"inefficiencies":[39],"when":[40],"crawling":[41],"pages":[43],"or":[44],"processing":[45],"user":[46],"queries.":[47],"this":[49],"work,":[50],"we":[51,145],"propose":[52],"a":[53,85,96,150],"machine-learned":[54],"document":[55,63,81,113,127],"assignment":[56,128],"strategy":[57,78],"that":[58,131],"uses":[59,92,107],"locality":[61],"views":[64],"in":[65],"results":[67],"decide":[69],"upon":[70],"assignments.":[71],"We":[72,116],"evaluate":[73],"our":[77,118,132,143],"using":[79],"various":[80],"features":[82],"extracted":[83],"large":[86],"collection.":[88],"Our":[89],"experimental":[90],"setup":[91],"query":[93,152],"logs":[94,109],"number":[97],"front-ends":[100],"spread":[101],"across":[102,168],"different":[103],"geographic":[104],"locations":[105],"these":[108],"learn":[111],"access":[114],"patterns.":[115],"compare":[117],"technique":[119,133],"against":[120],"baselines":[121],"as":[123],"region-":[124],"language-based":[126],"observe":[130],"achieves":[134],"substantial":[135],"improvements":[137],"with":[138],"respect":[139],"recall.":[141],"With":[142],"technique,":[144],"are":[146],"able":[147],"small":[151],"forwarding":[153],"rate":[154],"(0.04)":[155],"requiring":[156],"roughly":[157],"45%":[158],"less":[159],"replication":[160],"compared":[163],"replicating":[165],"all":[166,169]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
