{"id":"https://openalex.org/W2112006025","doi":"https://doi.org/10.1145/2682862.2682863","title":"Improvements to BM25 and Language Models Examined","display_name":"Improvements to BM25 and Language Models Examined","publication_year":2014,"publication_date":"2014-11-17","ids":{"openalex":"https://openalex.org/W2112006025","doi":"https://doi.org/10.1145/2682862.2682863","mag":"2112006025"},"language":"en","primary_location":{"id":"doi:10.1145/2682862.2682863","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2682862.2682863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Australasian Document Computing Symposium","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/A5050903724","display_name":"Andrew Trotman","orcid":"https://orcid.org/0000-0003-1253-7123"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Andrew Trotman","raw_affiliation_strings":["Department of Computer Science, University of Otago, Dunedin, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089859626","display_name":"Antti Puurula","orcid":null},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Antti Puurula","raw_affiliation_strings":["Department of Computer Science, University of Waikato, Hamilton, New Zealand","Department of Computer Science, University of Waikato, Hamilton, New zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]},{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007238545","display_name":"Blake Burgess","orcid":null},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Blake Burgess","raw_affiliation_strings":["Department of Computer Science, University of Otago, Dunedin, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050903724"],"corresponding_institution_ids":["https://openalex.org/I80281795"],"apc_list":null,"apc_paid":null,"fwci":15.5728,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.98757295,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983999729156494,"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":0.7995790243148804},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7522383332252502},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6462762355804443},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6331179141998291},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.608433187007904},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6006200909614563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.527075469493866},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5269290208816528},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5191299319267273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4191282391548157},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.1884332001209259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995790243148804},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7522383332252502},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6462762355804443},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6331179141998291},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.608433187007904},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6006200909614563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.527075469493866},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5269290208816528},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5191299319267273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4191282391548157},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.1884332001209259},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":1,"locations":[{"id":"doi:10.1145/2682862.2682863","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2682862.2682863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Australasian Document Computing Symposium","raw_type":"proceedings-article"}],"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":31,"referenced_works":["https://openalex.org/W95284390","https://openalex.org/W238053929","https://openalex.org/W1482214997","https://openalex.org/W1519066168","https://openalex.org/W1778535897","https://openalex.org/W1838897829","https://openalex.org/W1965647483","https://openalex.org/W1983903282","https://openalex.org/W1994922945","https://openalex.org/W2000569744","https://openalex.org/W2005545412","https://openalex.org/W2006996936","https://openalex.org/W2032854262","https://openalex.org/W2054160458","https://openalex.org/W2055775738","https://openalex.org/W2058200372","https://openalex.org/W2067073114","https://openalex.org/W2083551829","https://openalex.org/W2087696423","https://openalex.org/W2098162425","https://openalex.org/W2117562627","https://openalex.org/W2159024173","https://openalex.org/W2160160425","https://openalex.org/W2164547069","https://openalex.org/W2188152546","https://openalex.org/W2251286992","https://openalex.org/W2338896872","https://openalex.org/W4234200495","https://openalex.org/W6604569975","https://openalex.org/W6630333616","https://openalex.org/W6630826567"],"related_works":["https://openalex.org/W2382433580","https://openalex.org/W2100326285","https://openalex.org/W2369751049","https://openalex.org/W2198237484","https://openalex.org/W2150136235","https://openalex.org/W2053591227","https://openalex.org/W2041353081","https://openalex.org/W2581240705","https://openalex.org/W1972594981","https://openalex.org/W2045966063"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,9,38,46],"search":[3],"engine":[4],"ranking":[5,22],"functions":[6,23],"report":[7],"improvements":[8],"BM25":[10],"and":[11,32,44,49,81],"Language":[12],"Models":[13],"with":[14],"Dirichlet":[15],"Smoothing.":[16],"In":[17],"this":[18],"investigation":[19],"9":[20,50],"recent":[21],"(BM25,":[24],"BM25+,":[25],"BM25T,":[26],"BM25-adpt,":[27],"BM25L,":[28],"TF1\u00b0\u03b4\u00b0p\u00d7ID,":[29],"LM-DS,":[30],"LM-PYP,":[31],"LM-PYP-TFIDF)":[33],"are":[34],"compared":[35],"by":[36],"training":[37],"the":[39],"INEX":[40,47],"2009":[41],"Wikipedia":[42],"collection":[43],"testing":[45],"2010":[48],"TREC":[51],"collections.":[52],"We":[53],"find":[54],"that":[55,72,77,82],"once":[56],"trained":[57],"(using":[58],"particle":[59],"swarm":[60],"optimization)":[61],"there":[62],"is":[63,75,79,88],"very":[64],"little":[65],"difference":[66],"in":[67],"performance":[68],"between":[69],"these":[70],"functions,":[71],"relevance":[73],"feedback":[74],"effective,":[76,80],"stemming":[78],"it":[83],"remains":[84],"unclear":[85],"which":[86],"function":[87],"best":[89],"over-all.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}
