{"id":"https://openalex.org/W2005468737","doi":"https://doi.org/10.1145/2072221.2072240","title":"Indexing and weighting of multilingual and mixed documents","display_name":"Indexing and weighting of multilingual and mixed documents","publication_year":2011,"publication_date":"2011-10-03","ids":{"openalex":"https://openalex.org/W2005468737","doi":"https://doi.org/10.1145/2072221.2072240","mag":"2005468737"},"language":"en","primary_location":{"id":"doi:10.1145/2072221.2072240","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072221.2072240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the South African Institute of Computer Scientists and Information Technologists Conference on Knowledge, Innovation and Leadership in a Diverse, Multidisciplinary Environment","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/A5016675616","display_name":"Mohammed Mustafa","orcid":"https://orcid.org/0000-0002-1862-6429"},"institutions":[{"id":"https://openalex.org/I157614274","display_name":"University of Cape Town","ror":"https://ror.org/03p74gp79","country_code":"ZA","type":"education","lineage":["https://openalex.org/I157614274"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Mohammed Mustafa","raw_affiliation_strings":["University of Cape Town","University of Cape Town)"],"affiliations":[{"raw_affiliation_string":"University of Cape Town","institution_ids":["https://openalex.org/I157614274"]},{"raw_affiliation_string":"University of Cape Town)","institution_ids":["https://openalex.org/I157614274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111631144","display_name":"Izzedin Osman","orcid":null},"institutions":[{"id":"https://openalex.org/I9353105","display_name":"Sudan University of Science and Technology","ror":"https://ror.org/02fwtg066","country_code":"SD","type":"education","lineage":["https://openalex.org/I9353105"]}],"countries":["SD"],"is_corresponding":false,"raw_author_name":"Izzedin Osman","raw_affiliation_strings":["Sudan University of Science and Technology","Sudan University of Science & Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Sudan University of Science and Technology","institution_ids":["https://openalex.org/I9353105"]},{"raw_affiliation_string":"Sudan University of Science & Technology#TAB#","institution_ids":["https://openalex.org/I9353105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009415079","display_name":"Hussein Suleman","orcid":"https://orcid.org/0000-0002-4196-1444"},"institutions":[{"id":"https://openalex.org/I157614274","display_name":"University of Cape Town","ror":"https://ror.org/03p74gp79","country_code":"ZA","type":"education","lineage":["https://openalex.org/I157614274"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Hussein Suleman","raw_affiliation_strings":["University of Cape Town","University of Cape Town)"],"affiliations":[{"raw_affiliation_string":"University of Cape Town","institution_ids":["https://openalex.org/I157614274"]},{"raw_affiliation_string":"University of Cape Town)","institution_ids":["https://openalex.org/I157614274"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016675616"],"corresponding_institution_ids":["https://openalex.org/I157614274"],"apc_list":null,"apc_paid":null,"fwci":2.2168,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90441146,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9950000047683716,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9939000010490417,"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":0.8831567764282227},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7207853198051453},{"id":"https://openalex.org/keywords/cross-language-information-retrieval","display_name":"Cross-language information retrieval","score":0.6880912780761719},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6415058970451355},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.6397072672843933},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6323196291923523},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5874279737472534},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5574495792388916},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.5260531902313232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46198588609695435},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4506415128707886},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.4377315044403076},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.2857357859611511},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1914326250553131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8831567764282227},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7207853198051453},{"id":"https://openalex.org/C2778842860","wikidata":"https://www.wikidata.org/wiki/Q986551","display_name":"Cross-language information retrieval","level":3,"score":0.6880912780761719},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6415058970451355},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6397072672843933},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6323196291923523},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5874279737472534},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5574495792388916},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.5260531902313232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46198588609695435},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4506415128707886},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.4377315044403076},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2857357859611511},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1914326250553131},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2072221.2072240","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072221.2072240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the South African Institute of Computer Scientists and Information Technologists Conference on Knowledge, Innovation and Leadership in a Diverse, Multidisciplinary Environment","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310578","display_name":"University of Maryland","ror":"https://ror.org/01r0c1p88"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320324164","display_name":"University of Cape Town","ror":"https://ror.org/03p74gp79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W30790492","https://openalex.org/W1490022694","https://openalex.org/W1575967963","https://openalex.org/W1872098071","https://openalex.org/W1972583365","https://openalex.org/W1987226608","https://openalex.org/W1997682167","https://openalex.org/W2000635479","https://openalex.org/W2014415866","https://openalex.org/W2031685401","https://openalex.org/W2037320173","https://openalex.org/W2046456023","https://openalex.org/W2053584122","https://openalex.org/W2056324172","https://openalex.org/W2069870183","https://openalex.org/W2085030399","https://openalex.org/W2086253379","https://openalex.org/W2087648088","https://openalex.org/W2090955184","https://openalex.org/W2093976457","https://openalex.org/W2148212498","https://openalex.org/W2152577431","https://openalex.org/W2287442033","https://openalex.org/W4255459561"],"related_works":["https://openalex.org/W1594675583","https://openalex.org/W1514169108","https://openalex.org/W2142023570","https://openalex.org/W1531731103","https://openalex.org/W1593624979","https://openalex.org/W2404292891","https://openalex.org/W2397719058","https://openalex.org/W2389273994","https://openalex.org/W4248447766","https://openalex.org/W1603759061"],"abstract_inverted_index":{"Non-English-speaking":[0],"users,":[1],"such":[2],"as":[3],"Arabic":[4,25,53],"speakers,":[5],"are":[6,66,78,86,103,119,161,170],"not":[7,150],"always":[8],"able":[9],"to":[10,29,35,62,91,106,163,172],"express":[11],"terminology":[12],"in":[13,18,33,46,68,98,113],"their":[14],"native":[15],"languages,":[16],"especially":[17],"scientific":[19],"domains.":[20],"Such":[21],"difficulty":[22],"forces":[23],"many":[24],"authors":[26],"and":[27,52,117,124,131,136,158,160],"scholars":[28],"use":[30],"English":[31,51],"terms":[32,114],"order":[34],"explain":[36],"precise":[37],"concepts,":[38],"particularly":[39],"when":[40],"they":[41,85],"address":[42,92],"technical":[43],"topics,":[44],"resulting":[45],"mixed/multilingual":[47],"queries":[48,138,157],"with":[49],"both":[50],"terms.":[54],"Cross":[55],"Language":[56],"Information":[57],"Retrieval":[58],"(CLIR)":[59],"allows":[60],"users":[61],"search":[63],"documents":[64,135,159],"that":[65,102,145],"written":[67],"a":[69],"language":[70],"different":[71],"from":[72],"the":[73,93,107,167],"query.":[74],"However,":[75],"current":[76,146],"algorithms":[77],"optimized":[79],"for":[80,152],"monolingual":[81],"queries,":[82],"even":[83],"if":[84],"translated.":[87],"This":[88],"paper":[89],"attempts":[90],"problem":[94],"of":[95,110,115,155],"multilingual":[96,123,156],"querying":[97],"CLIR.":[99],"New":[100],"techniques":[101,148,169],"better":[104],"suited":[105],"unique":[108],"characteristics":[109],"this":[111],"problem,":[112],"indexing":[116],"weighting,":[118],"proposed.":[120],"A":[121],"new":[122],"mixed":[125],"test":[126],"collection":[127],"containing":[128],"mixed-language":[129,137],"(Arabic":[130],"English)":[132],"computer":[133],"science":[134],"has":[139],"been":[140],"created.":[141],"Experimentally,":[142],"results":[143],"show":[144],"CLIR":[147],"were":[149],"designed":[151],"these":[153],"types":[154],"found":[162,171],"perform":[164],"poorly":[165],"whereas":[166],"proposed":[168],"be":[173],"promising.":[174]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
