{"id":"https://openalex.org/W2059097316","doi":"https://doi.org/10.1145/2808194.2809486","title":"Verboseness Fission for BM25 Document Length Normalization","display_name":"Verboseness Fission for BM25 Document Length Normalization","publication_year":2015,"publication_date":"2015-09-22","ids":{"openalex":"https://openalex.org/W2059097316","doi":"https://doi.org/10.1145/2808194.2809486","mag":"2059097316"},"language":"en","primary_location":{"id":"doi:10.1145/2808194.2809486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808194.2809486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Conference on The Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058519912","display_name":"Aldo Lipani","orcid":"https://orcid.org/0000-0002-3643-6493"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aldo Lipani","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","(National Institute of Informatics, Tokyo, Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"(National Institute of Informatics, Tokyo, Japan)","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003585648","display_name":"Mihai Lupu","orcid":"https://orcid.org/0000-0002-6328-6873"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mihai Lupu","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria","Vienna University of technology, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna University of technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020665735","display_name":"Allan Hanbury","orcid":"https://orcid.org/0000-0002-7149-5843"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Allan Hanbury","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria","Vienna University of technology, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna University of technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041062417","display_name":"Akiko Aizawa","orcid":"https://orcid.org/0000-0001-6544-5076"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akiko Aizawa","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","(National Institute of Informatics, Tokyo, Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"(National Institute of Informatics, Tokyo, Japan)","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9984999895095825,"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/T13083","display_name":"Advanced Text Analysis Techniques","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/normalization","display_name":"Normalization (sociology)","score":0.8410935997962952},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7441393733024597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6974610090255737},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.44929683208465576},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4464607834815979},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4416664242744446},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43001458048820496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41232308745384216},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41037917137145996},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07565444707870483},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07367300987243652}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8410935997962952},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7441393733024597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974610090255737},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.44929683208465576},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4464607834815979},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4416664242744446},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43001458048820496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41232308745384216},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41037917137145996},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07565444707870483},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07367300987243652},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2808194.2809486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808194.2809486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Conference on The Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"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":20,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1502817561","https://openalex.org/W1763381236","https://openalex.org/W2000569744","https://openalex.org/W2005545412","https://openalex.org/W2032854262","https://openalex.org/W2061261643","https://openalex.org/W2066238291","https://openalex.org/W2068098598","https://openalex.org/W2083551829","https://openalex.org/W2087696423","https://openalex.org/W2105157020","https://openalex.org/W2105380208","https://openalex.org/W2111875680","https://openalex.org/W2141527751","https://openalex.org/W2155482025","https://openalex.org/W2887107689","https://openalex.org/W4234200495","https://openalex.org/W4252076394","https://openalex.org/W6628905179"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W2154177135","https://openalex.org/W2252747487","https://openalex.org/W2511569936","https://openalex.org/W4307413935","https://openalex.org/W3158697290"],"abstract_inverted_index":{"BM25":[0],"is":[1],"probably":[2],"the":[3,17,35,42,45,80,89,110,115],"most":[4],"well":[5],"known":[6],"term":[7],"weighting":[8],"model":[9],"in":[10,86],"Information":[11],"Retrieval.":[12],"It":[13],"has,":[14],"depending":[15],"on":[16,41,92],"formula":[18],"variant":[19],"at":[20],"hand,":[21],"2":[22],"or":[23],"3":[24],"parameters":[25],"(k1,":[26],"b,":[27],"and":[28,54,65,71],"k3).":[29],"This":[30],"paper":[31],"addresses":[32],"b":[33,84],"-":[34],"document":[36],"length":[37,51,75],"normalization":[38,52,76],"parameter.":[39],"Based":[40],"observation":[43],"that":[44,78,102],"two":[46],"cases":[47],"previously":[48],"discussed":[49],"for":[50,82,117],"(multi-topicality":[53],"verboseness)":[55],"are":[56],"actually":[57],"three:":[58],"multi-topicality,":[59],"verboseness":[60,66],"with":[61,67],"word":[62],"repetition":[63],"(repetitiveness)":[64],"synonyms,":[68],"we":[69,100,103],"propose":[70],"test":[72,98],"a":[73,83,93],"new":[74,90],"method":[77,91],"removes":[79],"need":[81,116],"parameter":[85],"BM25.":[87],"Testing":[88],"set":[94],"of":[95],"purposefully":[96],"varied":[97],"collections,":[99],"observe":[101],"can":[104],"obtain":[105],"results":[106],"statistically":[107],"indistinguishable":[108],"from":[109],"optimal":[111],"results,":[112],"therefore":[113],"removing":[114],"ground-truth":[118],"based":[119],"optimization.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}