{"id":"https://openalex.org/W201536428","doi":null,"title":"Inter-document similarities, language models, and ad hoc information retrieval","display_name":"Inter-document similarities, language models, and ad hoc information retrieval","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W201536428","mag":"201536428"},"language":"en","primary_location":{"id":"mag:201536428","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=1237197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5076876084","display_name":"Lillian Lee","orcid":"https://orcid.org/0000-0003-4770-1712","observed_orcids":["https://orcid.org/0000-0003-4770-1712","https://orcid.org/0000-0001-6577-9068"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lillian Lee","raw_affiliation_strings":["Cornell University"],"raw_orcid":"https://orcid.org/0000-0003-4770-1712","affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041210904","display_name":"Oren Kurland","orcid":"https://orcid.org/0000-0002-0669-0431","observed_orcids":["https://orcid.org/0000-0002-0669-0431"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oren Kurland","raw_affiliation_strings":["Cornell University"],"raw_orcid":"https://orcid.org/0000-0002-0669-0431","affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":10.8948,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.97648333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":1.0,"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":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/ad-hoc-retrieval","display_name":"ad hoc retrieval","score":0.9330000281333923},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.8009999990463257},{"id":"https://openalex.org/keywords/network-centrality","display_name":"network centrality","score":0.6930000185966492},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.8880000114440918},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.9300000071525574},{"id":"https://openalex.org/keywords/search-engines","display_name":"search engines","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8576864004135132},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7866050004959106},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.651374340057373},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5548424124717712},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.5309723615646362},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.477750688791275},{"id":"https://openalex.org/C21025794","wikidata":"https://www.wikidata.org/wiki/Q5141219","display_name":"Cognitive models of information retrieval","level":4,"score":0.4636704921722412},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4504094421863556},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.4381568431854248},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.43280890583992004},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41272154450416565},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37439191341400146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3384385108947754},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:201536428","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=1237197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":135,"referenced_works":["https://openalex.org/W25184121","https://openalex.org/W66569044","https://openalex.org/W80404851","https://openalex.org/W132343450","https://openalex.org/W201917955","https://openalex.org/W1483301080","https://openalex.org/W1486980688","https://openalex.org/W1490796714","https://openalex.org/W1497443639","https://openalex.org/W1501307387","https://openalex.org/W1514324734","https://openalex.org/W1514403774","https://openalex.org/W1515852583","https://openalex.org/W1519270649","https://openalex.org/W1525595230","https://openalex.org/W1526730373","https://openalex.org/W1534714852","https://openalex.org/W1585620735","https://openalex.org/W1592871157","https://openalex.org/W1594759534","https://openalex.org/W1605390201","https://openalex.org/W1660390307","https://openalex.org/W1803641895","https://openalex.org/W1880262756","https://openalex.org/W1904228841","https://openalex.org/W1928657940","https://openalex.org/W1963658069","https://openalex.org/W1964348731","https://openalex.org/W1965657003","https://openalex.org/W1971987737","https://openalex.org/W1972645849","https://openalex.org/W1975422446","https://openalex.org/W1975998118","https://openalex.org/W1979459060","https://openalex.org/W1981825277","https://openalex.org/W1985180788","https://openalex.org/W1988914905","https://openalex.org/W1989468977","https://openalex.org/W1990388042","https://openalex.org/W1992795877","https://openalex.org/W1993972354","https://openalex.org/W1996764654","https://openalex.org/W1999817920","https://openalex.org/W2000569744","https://openalex.org/W2003170434","https://openalex.org/W2005422315","https://openalex.org/W2006681603","https://openalex.org/W2015338694","https://openalex.org/W2018557178","https://openalex.org/W2019976352","https://openalex.org/W2021680564","https://openalex.org/W2021986193","https://openalex.org/W2022286021","https://openalex.org/W2026953311","https://openalex.org/W2027445772","https://openalex.org/W2028709054","https://openalex.org/W2030603245","https://openalex.org/W2041565863","https://openalex.org/W2042980227","https://openalex.org/W2043909051","https://openalex.org/W2047221353","https://openalex.org/W2048045485","https://openalex.org/W2053549370","https://openalex.org/W2058553017","https://openalex.org/W2061198046","https://openalex.org/W2062270497","https://openalex.org/W2063392856","https://openalex.org/W2064580901","https://openalex.org/W2066636486","https://openalex.org/W2066867064","https://openalex.org/W2067802667","https://openalex.org/W2068905009","https://openalex.org/W2073722401","https://openalex.org/W2074449313","https://openalex.org/W2077122984","https://openalex.org/W2079168273","https://openalex.org/W2083745421","https://openalex.org/W2084048649","https://openalex.org/W2084334506","https://openalex.org/W2093390569","https://openalex.org/W2095368471","https://openalex.org/W2097308346","https://openalex.org/W2097802284","https://openalex.org/W2099194852","https://openalex.org/W2099437808","https://openalex.org/W2100260099","https://openalex.org/W2100506586","https://openalex.org/W2100958137","https://openalex.org/W2102046030","https://openalex.org/W2102270039","https://openalex.org/W2109749916","https://openalex.org/W2110189854","https://openalex.org/W2110693578","https://openalex.org/W2110891728","https://openalex.org/W2111212948","https://openalex.org/W2111557120","https://openalex.org/W2114512077","https://openalex.org/W2114524997","https://openalex.org/W2114804204","https://openalex.org/W2117829666","https://openalex.org/W2119610041","https://openalex.org/W2120308175","https://openalex.org/W2121227244","https://openalex.org/W2123092185","https://openalex.org/W2127086485","https://openalex.org/W2127314673","https://openalex.org/W2129971563","https://openalex.org/W2130395434","https://openalex.org/W2131133093","https://openalex.org/W2132988481","https://openalex.org/W2133576408","https://openalex.org/W2134731454","https://openalex.org/W2136542423","https://openalex.org/W2136729221","https://openalex.org/W2138621811","https://openalex.org/W2141075029","https://openalex.org/W2144270295","https://openalex.org/W2146442558","https://openalex.org/W2147152072","https://openalex.org/W2150240006","https://openalex.org/W2152421703","https://openalex.org/W2153252192","https://openalex.org/W2158195707","https://openalex.org/W2158201212","https://openalex.org/W2158890594","https://openalex.org/W2159518412","https://openalex.org/W2160746453","https://openalex.org/W2162697159","https://openalex.org/W2162746367","https://openalex.org/W2164547069","https://openalex.org/W2165612380","https://openalex.org/W2169213601","https://openalex.org/W2187488439","https://openalex.org/W2787893582","https://openalex.org/W2916624877"],"related_works":["https://openalex.org/W2027445772","https://openalex.org/W2086298942","https://openalex.org/W7095106757","https://openalex.org/W1969413882","https://openalex.org/W4206765718","https://openalex.org/W2131133093","https://openalex.org/W7220748681","https://openalex.org/W2130395434","https://openalex.org/W2154575072","https://openalex.org/W2046902062"],"abstract_inverted_index":{"Search":[0],"engines":[1],"have":[2],"become":[3],"a":[4,37,48,51,107,116,251,318,330],"crucial":[5],"tool":[6],"for":[7,65,82,119,192,246,285],"finding":[8,34],"information":[9,30,44,59,83,127,140,224],"in":[10,18],"repositories":[11],"containing":[12],"large":[13],"amounts":[14],"of":[15,27,103,111,123,139,144,160,173,186,200,229,277,289,301,333],"textual":[16],"data":[17],"unstructured":[19],"form":[20],"(e.g.,":[21],"the":[22,25,101,104,121,137,174,183,201,211,219,230,238,275,299,311],"Web).":[23],"However,":[24,75],"task":[26,122],"ad":[28,124],"hoc":[29,125],"retrieval,":[31],"that":[32,39,147,156,164,167,172,182,254],"is,":[33],"documents":[35,146,202,290],"within":[36,218],"corpus":[38],"are":[40,148,157,326],"relevant":[41,334],"to":[42,58,89,205,256,297,328],"an":[43,62,196,222],"need":[45],"specified":[46],"using":[47,215],"query,":[49],"remains":[50],"hard":[52],"challenge.":[53],"\r\nThe":[54],"language":[55,80,92,131,176],"modeling":[56,177],"approach":[57,232],"retrieval":[60,84,154],"provides":[61],"effective":[63,278,320],"framework":[64,253],"approaching":[66,120],"various":[67],"problems":[68],"and":[69,94,163,235,240,243,291],"has":[70],"yielded":[71],"impressive":[72],"empirical":[73],"performance.":[74],"most":[76],"previous":[77],"work":[78],"on":[79,86],"models":[81,132],"focuses":[85],"document-specific":[87],"characteristics":[88],"estimate":[90],"documents'":[91],"models,":[93],"therefore":[95],"does":[96],"not":[97],"take":[98],"into":[99],"account":[100],"structure":[102],"surrounding":[105],"corpus,":[106],"potentially":[108],"rich":[109],"source":[110],"additional":[112],"information.":[113,261],"\r\nWe":[114],"present":[115,152],"novel":[117],"perspective":[118],"retrieval:":[126],"provided":[128],"by":[129,136,237,310],"document-based":[130],"can":[133],"be":[134],"enhanced":[135],"incorporation":[138],"drawn":[141],"from":[142],"clusters":[143,288,325],"similar":[145],"created":[149],"offline.":[150],"We":[151,179],"several":[153],"algorithms":[155,188,245],"natural":[158],"instantiations":[159],"this":[161],"idea":[162],"post":[165],"performance":[166,191],"is":[168,203,317],"substantially":[169],"better":[170],"than":[171],"standard":[175],"approach.":[178],"also":[180],"show":[181],"best":[184],"performing":[185],"these":[187],"posts":[189],"state-of-the-art":[190],"structural":[193],"re-ranking,":[194],"wherein":[195,267],"initially":[197],"retrieved":[198],"subset":[199],"re-ranked":[204],"obtain":[206],"high":[207,331],"precision":[208],"specifically":[209],"among":[210],"first":[212],"few":[213],"documents,":[214],"inter-document":[216,272],"similarities":[217,273],"list":[220],"as":[221,308],"extra":[223],"source.":[225],"\r\nAs":[226],"further":[227],"exploration":[228],"re-ranking":[231,279,321],"just":[233],"described,":[234],"inspired":[236],"PageRank":[239],"HITS":[241,312],"(hubs":[242],"authorities)":[244],"Web":[247],"search,":[248],"we":[249],"propose":[250],"graph-based":[252],"applies":[255],"document":[257,306],"collections":[258],"lacking":[259],"hyperlink":[260],"Specifically,":[262],"centrality":[263],"induced":[264,309],"over":[265,314],"graphs":[266,316],"links":[268,292],"represent":[269],"asymmetric":[270],"language-model-based":[271,294],"constitutes":[274],"basis":[276],"algorithms.":[280],"Combining":[281],"our":[282],"two":[283],"paradigms":[284],"similarity":[286],"representation---i.e.,":[287],"representing":[293],"inter-item":[295],"similarities---helps":[296],"improve":[298],"effectiveness":[300],"centrality-based":[302],"approaches.":[303],"For":[304],"example,":[305],"authoritativeness":[307],"algorithm":[313],"cluster-document":[315],"highly":[319],"criterion.":[322],"Furthermore,":[323],"authoritative":[324],"shown":[327],"contain":[329],"percentage":[332],"documents.":[335]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}