{"id":"https://openalex.org/W3096344723","doi":"https://doi.org/10.1108/dta-01-2019-0005","title":"Embedding based learning for collection selection in federated search","display_name":"Embedding based learning for collection selection in federated search","publication_year":2020,"publication_date":"2020-10-26","ids":{"openalex":"https://openalex.org/W3096344723","doi":"https://doi.org/10.1108/dta-01-2019-0005","mag":"3096344723"},"language":"en","primary_location":{"id":"doi:10.1108/dta-01-2019-0005","is_oa":false,"landing_page_url":"https://doi.org/10.1108/dta-01-2019-0005","pdf_url":null,"source":{"id":"https://openalex.org/S4210171756","display_name":"Data Technologies and Applications","issn_l":"2514-9288","issn":["2514-9288","2514-9318"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Technologies and Applications","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/A5087270473","display_name":"Adamu Garba","orcid":"https://orcid.org/0000-0001-7192-935X"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Adamu Garba","raw_affiliation_strings":["School of Computer and Communication Engineering, Jiangsu University, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006732432","display_name":"Shah Khalid","orcid":"https://orcid.org/0000-0001-5735-5863"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Shah Khalid","raw_affiliation_strings":["School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108013133","display_name":"Irfan Ullah","orcid":"https://orcid.org/0000-0003-0693-5467"},"institutions":[{"id":"https://openalex.org/I36001604","display_name":"University of Peshawar","ror":"https://ror.org/02t2qwf81","country_code":"PK","type":"education","lineage":["https://openalex.org/I36001604"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Irfan Ullah","raw_affiliation_strings":["Department of Computer Science, University of Peshawar, Peshawar, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Peshawar, Peshawar, Pakistan","institution_ids":["https://openalex.org/I36001604"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074454844","display_name":"Shah Khusro","orcid":"https://orcid.org/0000-0002-7734-7243"},"institutions":[{"id":"https://openalex.org/I36001604","display_name":"University of Peshawar","ror":"https://ror.org/02t2qwf81","country_code":"PK","type":"education","lineage":["https://openalex.org/I36001604"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Shah Khusro","raw_affiliation_strings":["Department of Computer Science, University of Peshawar, Peshawar, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Peshawar, Peshawar, Pakistan","institution_ids":["https://openalex.org/I36001604"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059041011","display_name":"Diyawu Mumin","orcid":"https://orcid.org/0000-0003-4941-5197"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diyawu Mumin","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087270473"],"corresponding_institution_ids":["https://openalex.org/I115592961"],"apc_list":null,"apc_paid":null,"fwci":1.0676,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84215338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"54","issue":"5","first_page":"703","last_page":"717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9986000061035156,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8266339302062988},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7156149744987488},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6853387355804443},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6499638557434082},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6252291798591614},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5072040557861328},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4997575283050537},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4972980320453644},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48886817693710327},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4887409210205078},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4579886198043823},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.43604201078414917},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4236440658569336},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3775099813938141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3066513240337372},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.10391679406166077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266339302062988},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7156149744987488},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6853387355804443},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6499638557434082},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6252291798591614},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5072040557861328},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4997575283050537},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4972980320453644},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48886817693710327},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4887409210205078},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4579886198043823},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.43604201078414917},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4236440658569336},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3775099813938141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3066513240337372},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.10391679406166077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/dta-01-2019-0005","is_oa":false,"landing_page_url":"https://doi.org/10.1108/dta-01-2019-0005","pdf_url":null,"source":{"id":"https://openalex.org/S4210171756","display_name":"Data Technologies and Applications","issn_l":"2514-9288","issn":["2514-9288","2514-9318"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Technologies and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2562782","https://openalex.org/W168564468","https://openalex.org/W232533489","https://openalex.org/W1854884267","https://openalex.org/W1986828474","https://openalex.org/W2002682102","https://openalex.org/W2003975698","https://openalex.org/W2005066702","https://openalex.org/W2028742638","https://openalex.org/W2038526807","https://openalex.org/W2043976122","https://openalex.org/W2054160068","https://openalex.org/W2068905009","https://openalex.org/W2113304843","https://openalex.org/W2117805756","https://openalex.org/W2121088496","https://openalex.org/W2128739123","https://openalex.org/W2147152072","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2252143362","https://openalex.org/W2346504203","https://openalex.org/W2484648951","https://openalex.org/W2510769428","https://openalex.org/W2515351093","https://openalex.org/W2521940885","https://openalex.org/W2596026555","https://openalex.org/W2765697536","https://openalex.org/W2801227764","https://openalex.org/W4245573484"],"related_works":["https://openalex.org/W2946409105","https://openalex.org/W3152932816","https://openalex.org/W2985392712","https://openalex.org/W3133567596","https://openalex.org/W4382201653","https://openalex.org/W2798009317","https://openalex.org/W4312127319","https://openalex.org/W2998070955","https://openalex.org/W2770162183","https://openalex.org/W3175524270"],"abstract_inverted_index":{"Purpose":[0],"There":[1],"have":[2],"been":[3],"many":[4,45],"challenges":[5],"in":[6,73,78,136],"crawling":[7],"deep":[8],"web":[9],"by":[10,30,202],"search":[11,43,52,77],"engines":[12],"due":[13],"to":[14,26,36,51,76,94,181],"their":[15],"proprietary":[16],"nature":[17],"or":[18],"dynamic":[19],"content.":[20],"Distributed":[21],"Information":[22],"Retrieval":[23],"(DIR)":[24],"tries":[25],"solve":[27],"these":[28,37,85],"problems":[29],"providing":[31],"a":[32,40,48,106],"unified":[33],"searchable":[34],"interface":[35],"databases.":[38],"Since":[39],"DIR":[41,100],"must":[42],"across":[44],"databases,":[46],"selecting":[47,74],"specific":[49],"database":[50],"against":[53],"the":[54,65,69,88,119,122,129,138,162,167,182,186,190],"user":[55],"query":[56],"is":[57,144,189],"challenging.":[58],"The":[59,103,142,156],"challenge":[60],"can":[61],"be":[62],"solved":[63],"if":[64],"past":[66,125,178,205],"queries":[67,179],"of":[68,99,192],"users":[70],"are":[71],"considered":[72],"collections":[75],"combination":[79],"with":[80],"word":[81,112,197],"embedding":[82,113,198],"techniques.":[83],"Combining":[84],"would":[86],"aid":[87],"best":[89,183],"performing":[90],"collection":[91,107,172,200],"selection":[92,108,173,201],"method":[93],"speed":[95],"up":[96],"retrieval":[97],"performance":[98],"solutions.":[101],"Design/methodology/approach":[102],"authors":[104],"propose":[105],"model":[109],"based":[110,176],"on":[111,177],"using":[114,146,174],"Word2Vec":[115],"approach":[116],"that":[117,195],"learns":[118],"similarity":[120,134,175],"between":[121],"current":[123],"and":[124,131],"queries.":[126,141,206],"They":[127],"used":[128],"cosine":[130,133],"transformed":[132],"models":[135,170],"computing":[137],"similarities":[139],"among":[140],"experiment":[143],"conducted":[145],"three":[147],"standard":[148],"TREC":[149],"testbeds":[150],"created":[151],"for":[152,171,199],"federated":[153],"search.":[154],"Findings":[155],"results":[157],"show":[158],"significant":[159],"improvements":[160],"over":[161],"baseline":[163],"models.":[164],"Originality/value":[165],"Although":[166],"lexical":[168],"matching":[169],"exist,":[180],"our":[184],"knowledge,":[185],"proposed":[187],"work":[188],"first":[191],"its":[193],"kind":[194],"uses":[196],"learning":[203],"from":[204]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}