{"id":"https://openalex.org/W225545357","doi":"https://doi.org/10.5220/0002017202790285","title":"ENHANCING HIGH PRECISION BY COMBINING OKAPI BM25 WITH STRUCTURAL SIMILARITY IN AN INFORMATION RETRIEVAL SYSTEM","display_name":"ENHANCING HIGH PRECISION BY COMBINING OKAPI BM25 WITH STRUCTURAL SIMILARITY IN AN INFORMATION RETRIEVAL SYSTEM","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W225545357","doi":"https://doi.org/10.5220/0002017202790285","mag":"225545357"},"language":"en","primary_location":{"id":"doi:10.5220/0002017202790285","doi":"https://doi.org/10.5220/0002017202790285","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0002017202790285","pdf_url":null,"source":{"id":"https://openalex.org/S4306419442","display_name":"International Conference on Enterprise Information Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Enterprise Information","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0002017202790285","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014973197","display_name":"Ya\u00ebl Champclaux","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ya\u00ebl Champclaux","raw_affiliation_strings":["Universit\u00e9 de Toulouse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Toulouse, France","institution_ids":["https://openalex.org/I4405258862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071901413","display_name":"Taoufiq Dkaki","orcid":"https://orcid.org/0000-0003-3962-7663","observed_orcids":["https://orcid.org/0000-0003-3962-7663"]},"institutions":[{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Taoufiq Dkaki","raw_affiliation_strings":["Universit\u00e9 de Toulouse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Toulouse, France","institution_ids":["https://openalex.org/I4405258862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035274820","display_name":"Josiane Mothe","orcid":"https://orcid.org/0000-0001-9273-2193","observed_orcids":["https://orcid.org/0000-0001-9273-2193"]},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Josiane Mothe","raw_affiliation_strings":["Universit\u00e9 de Toulouse, France","Institut de Recherche en Informatique de Toulouse"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Toulouse, France","institution_ids":["https://openalex.org/I4405258862"]},{"raw_affiliation_string":"Institut de Recherche en Informatique de Toulouse","institution_ids":["https://openalex.org/I4210119061"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2179,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.39150827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"285"},"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/T11269","display_name":"Algorithms and Data Compression","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/structural-similarity","display_name":"structural similarity","score":0.7229999899864197},{"id":"https://openalex.org/keywords/bm25","display_name":"BM25","score":0.9179999828338623},{"id":"https://openalex.org/keywords/similarity-measures","display_name":"similarity measures","score":0.652999997138977},{"id":"https://openalex.org/keywords/document-ranking","display_name":"document ranking","score":0.7440000176429749},{"id":"https://openalex.org/keywords/retrieval-precision","display_name":"retrieval precision","score":0.6129999756813049},{"id":"https://openalex.org/keywords/term-weighting","display_name":"term weighting","score":0.8029999732971191},{"id":"https://openalex.org/keywords/surface-similarity","display_name":"surface similarity","score":0.7879999876022339},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"cosine similarity","score":0.6660000085830688}],"concepts":[{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.875799298286438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804924249649048},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.749060869216919},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7305935025215149},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6711511611938477},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6167036294937134},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5917593836784363},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5456250309944153},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5022678375244141},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.48087671399116516},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.462485134601593},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4491182267665863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30427199602127075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.179296612739563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1311834454536438},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10945329070091248},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0002017202790285","doi":"https://doi.org/10.5220/0002017202790285","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0002017202790285","pdf_url":null,"source":{"id":"https://openalex.org/S4306419442","display_name":"International Conference on Enterprise Information Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Enterprise Information","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0002017202790285","doi":"https://doi.org/10.5220/0002017202790285","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0002017202790285","pdf_url":null,"source":{"id":"https://openalex.org/S4306419442","display_name":"International Conference on Enterprise Information Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Enterprise Information","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1573579329","https://openalex.org/W1978394996","https://openalex.org/W1979537657","https://openalex.org/W2001851376","https://openalex.org/W2008480878","https://openalex.org/W2009287352","https://openalex.org/W2060093866","https://openalex.org/W2078294512","https://openalex.org/W2098162425","https://openalex.org/W2103129421","https://openalex.org/W2113367658","https://openalex.org/W2120125686","https://openalex.org/W2135445920","https://openalex.org/W2138621811","https://openalex.org/W2147152072","https://openalex.org/W2153252192","https://openalex.org/W2158997610","https://openalex.org/W2165612380"],"related_works":["https://openalex.org/W4406969893","https://openalex.org/W1994792660","https://openalex.org/W642508044","https://openalex.org/W4254933859","https://openalex.org/W47863294","https://openalex.org/W2005878195","https://openalex.org/W2150534222","https://openalex.org/W2145883103","https://openalex.org/W3042117911","https://openalex.org/W2154575072"],"abstract_inverted_index":{"In":[0,80,100],"this":[1,101],"paper,":[2,102],"we":[3,84,103],"present":[4],"a":[5,29,34,57,81],"new":[6,58],"similarity":[7,91],"measure":[8],"in":[9,92],"the":[10,47,62,71,87,113,136],"context":[11],"of":[12,19,36,64,73,76,89],"Information":[13],"Retrieval":[14],"(IR).":[15],"The":[16],"main":[17],"objective":[18],"IR":[20],"systems":[21],"is":[22],"to":[23,28,107],"select":[24],"relevant":[25],"documents,":[26],"related":[27],"user\u201fs":[30],"information":[31],"need,":[32],"from":[33],"collection":[35],"documents.":[37,79],"Traditional":[38],"approaches":[39],"for":[40],"document/query":[41],"comparison":[42,48],"use":[43,63,88],"surface":[44,51,66],"similarity,":[45],"i.e.":[46],"engine":[49],"uses":[50],"attributes":[52],"(indexing":[53],"terms).":[54],"We":[55,116],"propose":[56],"method":[59,106],"which":[60],"combines":[61],"both":[65],"and":[67,124],"structural":[68,90,119],"similarities":[69,120],"with":[70,94],"aim":[72],"enhancing":[74],"precision":[75,123,125],"top":[77,127],"retrieved":[78,129],"previous":[82],"work,":[83],"showed":[85],"that":[86,118],"combination":[93],"cosine":[95,98],"improves":[96],"bare":[97],"ranking.":[99],"compare":[104],"our":[105],"Okapi":[108],"based":[109],"on":[110,112,140],"BM25":[111],"Cranfield":[114],"collection.":[115],"show":[117],"improve":[121],"average":[122],"at":[126],"10":[128],"documents":[130],"about":[131],"50%.":[132],"Experiments":[133],"also":[134],"address":[135],"term":[137],"weighting":[138],"influences":[139],"system":[141],"performances.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-06-24T00:00:00"}