{"id":"https://openalex.org/W1973153386","doi":"https://doi.org/10.1145/1148170.1148324","title":"Lightening the load of document smoothing for better language modeling retrieval","display_name":"Lightening the load of document smoothing for better language modeling retrieval","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W1973153386","doi":"https://doi.org/10.1145/1148170.1148324","mag":"1973153386"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148324","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual 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/A5049222552","display_name":"Mark D. Smucker","orcid":"https://orcid.org/0000-0003-4968-6405"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark D. Smucker","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034070218","display_name":"James Allan","orcid":"https://orcid.org/0000-0003-0132-5694"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Allan","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049222552"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.07933903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"699","last_page":"700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.998199999332428,"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":0.933573842048645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695655822753906},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6097313761711121},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5666685104370117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5633305907249451},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5238580703735352},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4024171233177185},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38425037264823914},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.12267184257507324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10429847240447998}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.933573842048645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695655822753906},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6097313761711121},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5666685104370117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5633305907249451},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5238580703735352},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4024171233177185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38425037264823914},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.12267184257507324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10429847240447998},{"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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1148170.1148324","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:ADA448634","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA448634","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.152.4228","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.152.4228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ciir.cs.umass.edu/pubfiles/ir-483.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2093390569","https://openalex.org/W2136542423","https://openalex.org/W2162746367","https://openalex.org/W4206765718","https://openalex.org/W4240913316"],"related_works":["https://openalex.org/W2382433580","https://openalex.org/W2100326285","https://openalex.org/W2369751049","https://openalex.org/W2198237484","https://openalex.org/W2041122820","https://openalex.org/W1978572805","https://openalex.org/W2381981226","https://openalex.org/W1972594981","https://openalex.org/W2136542423","https://openalex.org/W2045966063"],"abstract_inverted_index":{"We":[0,25],"hypothesized":[1],"that":[2,79],"language":[3],"modeling":[4,85],"retrieval":[5,86],"would":[6],"improve":[7],"if":[8],"we":[9],"reduced":[10],"the":[11,40,53],"need":[12],"for":[13],"document":[14,20,44,76,100],"smoothing":[15,77],"to":[16,37,47,92],"provide":[17],"an":[18,95],"inverse":[19,27],"frequency":[21,29],"(IDF)":[22],"like":[23],"effect.":[24],"created":[26],"collection":[28],"(ICF)":[30],"weighted":[31,55,70],"query":[32],"models":[33],"as":[34],"a":[35,58,90],"tool":[36],"partially":[38],"separate":[39],"IDF-like":[41,96],"role":[42],"from":[43,89],"smoothing.":[45,101],"Compared":[46],"maximum":[48],"likelihood":[49],"estimated":[50],"(MLE)":[51],"queries,":[52],"ICF":[54,69],"queries":[56,71],"achieved":[57],"6.4\\%":[59],"improvement":[60],"in":[61],"mean":[62],"average":[63],"precision":[64],"on":[65],"description":[66],"queries.":[67,83],"The":[68],"performed":[72],"better":[73],"with":[74],"less":[75],"than":[78],"required":[80],"by":[81],"MLE":[82],"Language":[84],"may":[87],"benefit":[88],"means":[91],"separately":[93],"incorporate":[94],"behavior":[97],"outside":[98],"of":[99]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}