{"id":"https://openalex.org/W1994519941","doi":"https://doi.org/10.1109/iscc.2008.4625724","title":"OOV words in an English-Arabic CLIR system","display_name":"OOV words in an English-Arabic CLIR system","publication_year":2008,"publication_date":"2008-07-01","ids":{"openalex":"https://openalex.org/W1994519941","doi":"https://doi.org/10.1109/iscc.2008.4625724","mag":"1994519941"},"language":"en","primary_location":{"id":"doi:10.1109/iscc.2008.4625724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc.2008.4625724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Symposium on Computers and Communications","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/A5069118483","display_name":"Abdelghani Bellaachia","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdelghani Bellaachia","raw_affiliation_strings":["Department of Computer Science, The George Washington University, Washington DC, USA","Department of Computer Science, George Washington University, Washington, DC#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The George Washington University, Washington DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Department of Computer Science, George Washington University, Washington, DC#TAB#","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010323333","display_name":"Ghita Amor\u2010Tijani","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghita AmorTijani","raw_affiliation_strings":["The George Washington University, Department of Computer Science, DC 20052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The George Washington University, Department of Computer Science, DC 20052, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08401584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"874","last_page":"882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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":0.9915000200271606,"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":0.8507909774780273},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.8462948203086853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7257963418960571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6848013401031494},{"id":"https://openalex.org/keywords/proper-noun","display_name":"Proper noun","score":0.6482582688331604},{"id":"https://openalex.org/keywords/cross-language-information-retrieval","display_name":"Cross-language information retrieval","score":0.6381238102912903},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.4865387976169586},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47386670112609863},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.42066675424575806},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3514949679374695},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.267315149307251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507909774780273},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8462948203086853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7257963418960571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848013401031494},{"id":"https://openalex.org/C41417386","wikidata":"https://www.wikidata.org/wiki/Q147276","display_name":"Proper noun","level":2,"score":0.6482582688331604},{"id":"https://openalex.org/C2778842860","wikidata":"https://www.wikidata.org/wiki/Q986551","display_name":"Cross-language information retrieval","level":3,"score":0.6381238102912903},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.4865387976169586},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47386670112609863},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.42066675424575806},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3514949679374695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.267315149307251},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscc.2008.4625724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc.2008.4625724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Symposium on Computers and Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W51309311","https://openalex.org/W311963822","https://openalex.org/W1577446279","https://openalex.org/W1596452390","https://openalex.org/W1599955416","https://openalex.org/W1985833281","https://openalex.org/W2018378073","https://openalex.org/W2044157185","https://openalex.org/W2056724340","https://openalex.org/W2093537029","https://openalex.org/W2098162425","https://openalex.org/W2134534213","https://openalex.org/W2151858239","https://openalex.org/W2168965629","https://openalex.org/W2913739034","https://openalex.org/W6611036236","https://openalex.org/W6634334885","https://openalex.org/W6635522034","https://openalex.org/W6703490699"],"related_works":["https://openalex.org/W308894259","https://openalex.org/W1985769368","https://openalex.org/W4249525869","https://openalex.org/W32666253","https://openalex.org/W128271544","https://openalex.org/W4240166664","https://openalex.org/W153409568","https://openalex.org/W2021214750","https://openalex.org/W4389584227","https://openalex.org/W29321772"],"abstract_inverted_index":{"Proper":[0],"nouns":[1],"are":[2,46,98,152],"usually":[3,174],"primary":[4],"keys":[5],"in":[6,21,52],"a":[7,17,22,176,181],"query.":[8],"Their":[9],"correct":[10],"translation":[11],"might":[12],"be":[13,86],"necessary":[14],"to":[15,71,85,114,121,193,200],"maintain":[16],"good":[18],"retrieval":[19,26],"performance":[20],"cross":[23],"language":[24,75,147],"information":[25],"(CLIR)":[27],"system.":[28],"However,":[29],"dictionaries":[30],"only":[31],"include":[32],"the":[33,62,67,73,78,87,118,123,145,161,164,202,208],"most":[34,53,88],"commonly":[35],"used":[36,179],"proper":[37,171],"nouns,":[38],"like":[39],"major":[40],"countries":[41],"and":[42],"capitals.":[43],"As":[44,96],"they":[45],"spelling":[47,125],"variants":[48,126],"of":[49,77,109,127,129,163,196,204],"each":[50],"other":[51,91],"languages,":[54],"using":[55,212],"an":[56,101],"approximate":[57,92],"string":[58,93],"matching":[59,94],"technique":[60,83,120],"against":[61],"target":[63,74],"database":[64],"index":[65],"is":[66,148,167],"common":[68],"approach":[69],"taken":[70],"find":[72],"correspondents":[76],"original":[79],"query":[80],"key.":[81],"N-gram":[82],"proved":[84],"effective":[89],"among":[90],"techniques.":[95],"we":[97,112,191],"dealing":[99],"with":[100,117,144],"English-Arabic":[102],"CLIR":[103],"system":[104],"which":[105,173],"involves":[106],"two":[107],"languages":[108],"different":[110,124,157],"alphabets,":[111],"decided":[113],"combine":[115],"transliteration":[116,189],"n-gram":[119],"generate":[122],"out":[128],"vocabulary":[130],"(OOV)":[131],"words.":[132],"We":[133],"call":[134],"this":[135],"technique:":[136],"Transliteration":[137],"Ngram":[138],"(TNG).":[139],"One":[140],"issue":[141],"that":[142,149,151],"arises":[143],"Arabic":[146],"words":[150,206],"spelled":[153],"similarly":[154],"can":[155],"have":[156,175],"meanings":[158],"depending":[159],"on":[160],"context":[162],"sentence.":[165],"This":[166],"particularly":[168],"true":[169],"for":[170],"names,":[172],"meaning":[177],"if":[178],"as":[180],"verb":[182],"or":[183],"adjective.":[184],"To":[185],"further":[186],"enhance":[187],"our":[188],"approach,":[190],"chose":[192],"use":[194],"part":[195],"speech":[197],"(POS)":[198],"disambiguation":[199],"reduce":[201],"number":[203],"unrelated":[205],"from":[207],"set":[209],"transliterations":[210],"obtained":[211],"TNG.":[213]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}