{"id":"https://openalex.org/W2159981039","doi":"https://doi.org/10.1145/2009916.2010058","title":"Pseudo test collections for learning web search ranking functions","display_name":"Pseudo test collections for learning web search ranking functions","publication_year":2011,"publication_date":"2011-07-24","ids":{"openalex":"https://openalex.org/W2159981039","doi":"https://doi.org/10.1145/2009916.2010058","mag":"2159981039"},"language":"en","primary_location":{"id":"doi:10.1145/2009916.2010058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th 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/A5048421272","display_name":"Nima Asadi","orcid":"https://orcid.org/0000-0002-5102-6927"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nima Asadi","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000115067","display_name":"Donald Metzler","orcid":"https://orcid.org/0000-0003-4276-6269"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald Metzler","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032141720","display_name":"Tamer Elsayed","orcid":"https://orcid.org/0000-0001-5786-4668"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Tamer Elsayed","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048421272"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":6.1155,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96225007,"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":"1073","last_page":"1082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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":0.9945999979972839,"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":0.8311066627502441},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7997927069664001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.715824544429779},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.6249433159828186},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5849578380584717},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.533930778503418},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4915665090084076},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4751693606376648},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4708176255226135},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.42633628845214844},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.41135865449905396},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.41073596477508545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40885472297668457},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36172735691070557},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.3019108772277832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311066627502441},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7997927069664001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.715824544429779},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.6249433159828186},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5849578380584717},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.533930778503418},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4915665090084076},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4751693606376648},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4708176255226135},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.42633628845214844},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.41135865449905396},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41073596477508545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40885472297668457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36172735691070557},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3019108772277832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2009916.2010058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.222.5010","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.222.5010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.umiacs.umd.edu/%7Ejimmylin/publications/Asadi_etal_SIGIR2011.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.229.1491","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.1491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/Grad/scholarlypapers/papers/NimaAsadi.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.465.5930","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.465.5930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://don-metzler.net/papers/fp301-asadi.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W132882894","https://openalex.org/W1581508697","https://openalex.org/W1685426458","https://openalex.org/W1854214752","https://openalex.org/W1973435495","https://openalex.org/W1973836822","https://openalex.org/W1983595289","https://openalex.org/W1994960885","https://openalex.org/W2013722041","https://openalex.org/W2040337753","https://openalex.org/W2047221353","https://openalex.org/W2053100920","https://openalex.org/W2066781816","https://openalex.org/W2067802667","https://openalex.org/W2069870183","https://openalex.org/W2073448073","https://openalex.org/W2080825533","https://openalex.org/W2089199911","https://openalex.org/W2096346879","https://openalex.org/W2099391294","https://openalex.org/W2106421124","https://openalex.org/W2106927287","https://openalex.org/W2113537486","https://openalex.org/W2113640060","https://openalex.org/W2124108136","https://openalex.org/W2124504084","https://openalex.org/W2131343135","https://openalex.org/W2132232498","https://openalex.org/W2134099522","https://openalex.org/W2134131174","https://openalex.org/W2138621811","https://openalex.org/W2142537246","https://openalex.org/W2143331230","https://openalex.org/W2143806604","https://openalex.org/W2147057843","https://openalex.org/W2149427297","https://openalex.org/W2152314154","https://openalex.org/W2156160882","https://openalex.org/W2156577800","https://openalex.org/W2165903295","https://openalex.org/W2949909718","https://openalex.org/W6605431065","https://openalex.org/W6639055396"],"related_works":["https://openalex.org/W2122840831","https://openalex.org/W2140951215","https://openalex.org/W2967976110","https://openalex.org/W1584968907","https://openalex.org/W2123994076","https://openalex.org/W1540194478","https://openalex.org/W2031812225","https://openalex.org/W2043257601","https://openalex.org/W2889658777","https://openalex.org/W2550180686"],"abstract_inverted_index":{"Test":[0],"collections":[1,43,61,162],"are":[2,97,110,169],"the":[3,16,54,83,180],"primary":[4],"drivers":[5],"of":[6,18,41,56,105,115,182],"progress":[7],"in":[8,21,62,185],"information":[9],"retrieval.":[10],"They":[11],"provide":[12],"yardsticks":[13],"for":[14,33,140],"assessing":[15],"effectiveness":[17],"ranking":[19,142,166],"functions":[20],"an":[22,164],"automatic,":[23],"rapid,":[24],"and":[25,28,49,107,120,129,168],"repeatable":[26],"fashion":[27],"serve":[29],"as":[30,73,88],"training":[31,141,189],"data":[32,151,190],"learning":[34,154],"to":[35,45,155],"rank":[36,156],"models.":[37],"However,":[38],"manual":[39,177],"construction":[40],"test":[42,60,134,161],"tends":[44],"be":[46,138],"slow,":[47],"labor-intensive,":[48],"expensive.":[50],"This":[51],"paper":[52],"examines":[53],"feasibility":[55],"constructing":[57],"web":[58,71,84,149],"search":[59],"a":[63,69,89,103,113,132,173],"completely":[64],"unsupervised":[65,165],"manner":[66],"given":[67],"only":[68],"large":[70],"corpus":[72],"input.":[74],"Within":[75],"our":[76,183],"proposed":[77],"framework,":[78],"anchor":[79,122],"text":[80,123],"extracted":[81],"from":[82,93,172],"graph":[85],"is":[86],"treated":[87],"pseudo":[90,95,101,133,160],"query":[91],"log":[92],"which":[94],"queries":[96,128],"sampled.":[98],"For":[99],"each":[100],"query,":[102],"set":[104],"relevant":[106],"non-relevant":[108],"documents":[109],"selected":[111],"using":[112,159,176],"variety":[114],"web-specific":[116],"features,":[117],"including":[118],"spam":[119],"aggregated":[121],"weights.":[124],"The":[125],"automatically":[126],"mined":[127],"judgments":[130],"form":[131],"collection":[135],"that":[136,153],"can":[137],"used":[139],"functions.":[143],"Experiments":[144],"carried":[145],"out":[146],"on":[147],"TREC":[148],"track":[150],"show":[152],"models":[157],"trained":[158,175],"outperform":[163],"function":[167],"statistically":[170],"indistinguishable":[171],"model":[174],"judgments,":[178],"demonstrating":[179],"usefulness":[181],"approach":[184],"extracting":[186],"reasonable":[187],"quality":[188],"\"for":[191],"free\".":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}