{"id":"https://openalex.org/W2136542423","doi":"https://doi.org/10.1145/3130348.3130377","title":"A Study of Smoothing Methods for Language Models Applied to Ad Hoc Information Retrieval","display_name":"A Study of Smoothing Methods for Language Models Applied to Ad Hoc Information Retrieval","publication_year":2017,"publication_date":"2017-08-02","ids":{"openalex":"https://openalex.org/W2136542423","doi":"https://doi.org/10.1145/3130348.3130377","mag":"2136542423"},"language":"en","primary_location":{"id":"doi:10.1145/3130348.3130377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3130348.3130377","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-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/A5028518494","display_name":"ChengXiang Zhai","orcid":"https://orcid.org/0000-0002-6434-3702"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chengxiang Zhai","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060219657","display_name":"John Lafferty","orcid":"https://orcid.org/0000-0002-5929-220X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Lafferty","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028518494"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":146.1779,"has_fulltext":false,"cited_by_count":1571,"citation_normalized_percentile":{"value":0.99967886,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"51","issue":"2","first_page":"268","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9919000267982483,"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/smoothing","display_name":"Smoothing","score":0.9129713773727417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.90018630027771},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8273636102676392},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6253592371940613},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5911304950714111},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42272526025772095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4224322736263275},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3751583993434906},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3698839545249939},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35820794105529785},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1353565752506256}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.9129713773727417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.90018630027771},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8273636102676392},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6253592371940613},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5911304950714111},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42272526025772095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4224322736263275},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3751583993434906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3698839545249939},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35820794105529785},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1353565752506256},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1145/3130348.3130377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3130348.3130377","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.8113","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.8113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~lafferty/pub/smooth.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.29.1052","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.1052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/afs/cs/project/link-3/lafferty/www/ps/smooth.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.335.612","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.335.612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iro.umontreal.ca/~nie/IFT6255/zhai-lafferty.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.1656","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.1656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~lafferty/pub/smooth.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.9792","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.9792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sifaka.cs.uiuc.edu/czhai/pub/sigir2001-smooth.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.4611","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.4611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aladdin.cs.cmu.edu/papers/pdfs/y2001/smooth.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.7623","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.7623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sifaka.cs.uiuc.edu/czhai/pub/zhai-paper1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.6272","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.6272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hachita.nmsu.edu/ref/zhai01study.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1540124269","https://openalex.org/W1553682320","https://openalex.org/W1597533204","https://openalex.org/W1934041838","https://openalex.org/W1965282483","https://openalex.org/W1974413746","https://openalex.org/W1978394996","https://openalex.org/W1989468977","https://openalex.org/W2000569744","https://openalex.org/W2000672666","https://openalex.org/W2026937586","https://openalex.org/W2047031127","https://openalex.org/W2062270497","https://openalex.org/W2068905009","https://openalex.org/W2075201173","https://openalex.org/W2082092506","https://openalex.org/W2093390569","https://openalex.org/W2095368471","https://openalex.org/W2099437808","https://openalex.org/W2100279283","https://openalex.org/W2132957691","https://openalex.org/W2134237567","https://openalex.org/W2136583886","https://openalex.org/W2136729221","https://openalex.org/W2155520241","https://openalex.org/W2158195707","https://openalex.org/W2165612380","https://openalex.org/W2169213601","https://openalex.org/W2272751671","https://openalex.org/W4206765718","https://openalex.org/W4234200495","https://openalex.org/W4245107743","https://openalex.org/W4249191614","https://openalex.org/W6628905179","https://openalex.org/W6632313116"],"related_works":["https://openalex.org/W2383807498","https://openalex.org/W1978572805","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W1972594981","https://openalex.org/W2045966063"],"abstract_inverted_index":{"Language":[0],"modeling":[1],"approaches":[2,41],"to":[3,43,62,84,89,116],"information":[4],"retrieval":[5,16,107,114],"are":[6],"attractive":[7],"and":[8,51,103,120],"promising":[9],"because":[10],"they":[11],"connect":[12],"the":[13,56,59,63,78,86,97,111,117],"problem":[14,69,98],"of":[15,19,39,58,99,113],"with":[17],"that":[18],"language":[20,46,65,71,100],"model":[21,47,72,101],"estimation,":[22],"which":[23,76],"has":[24],"been":[25],"studied":[26],"extensively":[27],"in":[28,70],"other":[29],"application":[30],"areas":[31],"such":[32],"as":[33,83],"speech":[34],"recognition.":[35],"The":[36],"basic":[37],"idea":[38],"these":[40],"is":[42,74],"estimate":[44],"a":[45],"for":[48],"each":[49],"document,":[50],"then":[52],"rank":[53],"documents":[54],"by":[55],"likelihood":[57,80],"query":[60],"according":[61],"estimated":[64],"model.":[66],"A":[67],"core":[68],"estimation":[73],"smoothing,":[75],"adjusts":[77],"maximum":[79],"estimator":[81],"so":[82],"correct":[85],"inaccuracy":[87],"due":[88],"data":[90],"sparseness.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95],"study":[96],"smoothing":[102,118,124],"its":[104],"influence":[105],"on":[106,126],"performance.":[108],"We":[109],"examine":[110],"sensitivity":[112],"performance":[115],"parameters":[119],"compare":[121],"several":[122],"popular":[123],"methods":[125],"different":[127],"test":[128],"collection.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":60},{"year":2019,"cited_by_count":71},{"year":2018,"cited_by_count":87},{"year":2017,"cited_by_count":71},{"year":2016,"cited_by_count":93},{"year":2015,"cited_by_count":97},{"year":2014,"cited_by_count":92},{"year":2013,"cited_by_count":92},{"year":2012,"cited_by_count":107}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}