{"id":"https://openalex.org/W4391017630","doi":"https://doi.org/10.1162/coli_a_00510","title":"Context-aware Transliteration of Romanized South Asian Languages","display_name":"Context-aware Transliteration of Romanized South Asian Languages","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4391017630","doi":"https://doi.org/10.1162/coli_a_00510"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00510","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00510","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00510/2213805/coli_a_00510.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"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":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00510/2213805/coli_a_00510.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063051593","display_name":"Christo Kirov","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christo Kirov","raw_affiliation_strings":["Google Research. ckirov@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research. ckirov@google.com","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063164740","display_name":"Cibu Johny","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cibu Johny","raw_affiliation_strings":["Google Research. cibu@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research. cibu@google.com","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054501249","display_name":"Anna Katanova","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Katanova","raw_affiliation_strings":["Google Research. akatanova@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research. akatanova@google.com","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029193854","display_name":"Alexander Gutkin","orcid":"https://orcid.org/0000-0001-6327-4824"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Gutkin","raw_affiliation_strings":["Google Research. agutkin@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research. agutkin@google.com","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020068498","display_name":"Brian Roark","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Roark","raw_affiliation_strings":["Google Research. roark@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research. roark@google.com","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063051593"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.011,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81857305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"50","issue":"2","first_page":"475","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10759","display_name":"Translation Studies and Practices","score":0.9666000008583069,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9218999743461609,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/transliteration","display_name":"Transliteration","score":0.932869553565979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8736767768859863},{"id":"https://openalex.org/keywords/romanization","display_name":"Romanization","score":0.8596206903457642},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7633242607116699},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6596794724464417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6564558744430542},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.584707498550415},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4288058280944824},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26139095425605774},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06279164552688599}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.932869553565979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8736767768859863},{"id":"https://openalex.org/C106930687","wikidata":"https://www.wikidata.org/wiki/Q976327","display_name":"Romanization","level":2,"score":0.8596206903457642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7633242607116699},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6596794724464417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6564558744430542},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.584707498550415},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4288058280944824},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26139095425605774},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06279164552688599},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00510","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00510","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00510/2213805/coli_a_00510.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"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":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:96736b6a07b7433bad2c256c600f4856","is_oa":true,"landing_page_url":"https://doaj.org/article/96736b6a07b7433bad2c256c600f4856","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 50, Iss 2 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00510","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00510","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00510/2213805/coli_a_00510.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"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":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313434","display_name":"Institute for Catastrophic Loss Reduction","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391017630.pdf"},"referenced_works_count":136,"referenced_works":["https://openalex.org/W67332896","https://openalex.org/W572161410","https://openalex.org/W644009243","https://openalex.org/W1506201763","https://openalex.org/W1508165687","https://openalex.org/W1522301498","https://openalex.org/W1559169059","https://openalex.org/W1570629387","https://openalex.org/W1582482241","https://openalex.org/W1592736283","https://openalex.org/W1647671624","https://openalex.org/W1902237438","https://openalex.org/W1934041838","https://openalex.org/W1978489870","https://openalex.org/W2007321142","https://openalex.org/W2012557190","https://openalex.org/W2019470056","https://openalex.org/W2019614587","https://openalex.org/W2055543848","https://openalex.org/W2064675550","https://openalex.org/W2066792529","https://openalex.org/W2088416582","https://openalex.org/W2090755665","https://openalex.org/W2113641473","https://openalex.org/W2121879602","https://openalex.org/W2125528794","https://openalex.org/W2125838338","https://openalex.org/W2130266733","https://openalex.org/W2132714218","https://openalex.org/W2133564696","https://openalex.org/W2134587001","https://openalex.org/W2138294949","https://openalex.org/W2151952699","https://openalex.org/W2166660646","https://openalex.org/W2183280750","https://openalex.org/W2250967669","https://openalex.org/W2251467004","https://openalex.org/W2251734840","https://openalex.org/W2338181011","https://openalex.org/W2407405674","https://openalex.org/W2471408330","https://openalex.org/W2488800812","https://openalex.org/W2514457011","https://openalex.org/W2539033431","https://openalex.org/W2560674852","https://openalex.org/W2602331152","https://openalex.org/W2604799257","https://openalex.org/W2612690371","https://openalex.org/W2613000335","https://openalex.org/W2621262511","https://openalex.org/W2746762542","https://openalex.org/W2793017812","https://openalex.org/W2805411799","https://openalex.org/W2809687772","https://openalex.org/W2884873108","https://openalex.org/W2885158679","https://openalex.org/W2887185954","https://openalex.org/W2889326796","https://openalex.org/W2895340766","https://openalex.org/W2901114707","https://openalex.org/W2904008843","https://openalex.org/W2912273839","https://openalex.org/W2924677654","https://openalex.org/W2963216553","https://openalex.org/W2963250244","https://openalex.org/W2963919854","https://openalex.org/W2964045208","https://openalex.org/W2964084554","https://openalex.org/W2972495969","https://openalex.org/W2979026328","https://openalex.org/W2980576249","https://openalex.org/W2983577274","https://openalex.org/W3010838151","https://openalex.org/W3015564377","https://openalex.org/W3035390927","https://openalex.org/W3037582736","https://openalex.org/W3093721400","https://openalex.org/W3101567131","https://openalex.org/W3102783139","https://openalex.org/W3137010024","https://openalex.org/W3155028086","https://openalex.org/W3156496359","https://openalex.org/W3156789018","https://openalex.org/W3164045210","https://openalex.org/W3169244955","https://openalex.org/W3169483174","https://openalex.org/W3177682494","https://openalex.org/W3198214208","https://openalex.org/W3198690080","https://openalex.org/W3199212312","https://openalex.org/W3200927912","https://openalex.org/W3214173179","https://openalex.org/W4224442590","https://openalex.org/W4234453845","https://openalex.org/W4234927774","https://openalex.org/W4240166664","https://openalex.org/W4256161595","https://openalex.org/W4285289306","https://openalex.org/W4285296929","https://openalex.org/W4288089799","https://openalex.org/W4293005022","https://openalex.org/W4295308551","https://openalex.org/W4307308004","https://openalex.org/W4318239774","https://openalex.org/W4385570009","https://openalex.org/W4385570911","https://openalex.org/W4385571195","https://openalex.org/W4385572099","https://openalex.org/W4385572278","https://openalex.org/W4385574296","https://openalex.org/W4386576703","https://openalex.org/W4389523734","https://openalex.org/W6601696544","https://openalex.org/W6602788574","https://openalex.org/W6606341813","https://openalex.org/W6628119961","https://openalex.org/W6630297505","https://openalex.org/W6630547646","https://openalex.org/W6631190155","https://openalex.org/W6636915900","https://openalex.org/W6679317074","https://openalex.org/W6679434410","https://openalex.org/W6682082992","https://openalex.org/W6684316753","https://openalex.org/W6691268121","https://openalex.org/W6703490699","https://openalex.org/W6705120047","https://openalex.org/W6721138529","https://openalex.org/W6739901393","https://openalex.org/W6748347909","https://openalex.org/W6752933292","https://openalex.org/W6769627184","https://openalex.org/W6778531586","https://openalex.org/W6778778454","https://openalex.org/W6788886565","https://openalex.org/W6838684745"],"related_works":["https://openalex.org/W4293756708","https://openalex.org/W4389731935","https://openalex.org/W4377080406","https://openalex.org/W2808928361","https://openalex.org/W2395524355","https://openalex.org/W4387031027","https://openalex.org/W2188293928","https://openalex.org/W2186822451","https://openalex.org/W4318002233","https://openalex.org/W2069398544"],"abstract_inverted_index":{"Abstract":[0],"While":[1],"most":[2,27],"transliteration":[3,15,47,73,94,164],"research":[4],"is":[5,129],"focused":[6],"on":[7,148,170],"single":[8,64],"tokens":[9],"such":[10,77,98],"as":[11,78],"named":[12],"entities\u2014for":[13],"example,":[14],"of":[16,34,48,53,58,69,90,103,113,120],"from":[17,165],"the":[18,22,31,36,121,156,175],"Gujarati":[19],"script":[20,24,169],"to":[21,63,123,167],"Latin":[23,166],"\u201cAhmedabad\u201d":[25],"footnoteThe":[26],"populous":[28],"city":[29],"in":[30,40,95,106,127,174],"Indian":[32],"state":[33],"Gujarat.":[35],"informal":[37],"romanization":[38],"prevalent":[39],"South":[41],"Asia":[42],"and":[43],"elsewhere":[44],"often":[45],"requires":[46],"full":[49,59,162],"sentences.":[50],"The":[51],"lack":[52],"large":[54,143],"parallel":[55,150],"text":[56,81],"collections":[57],"sentence":[60,163],"(as":[61],"opposed":[62],"word)":[65],"transliterations":[66],"necessitates":[67],"incorporation":[68],"contextual":[70,125],"information":[71,126],"into":[72],"via":[74,79],"non-parallel":[75],"resources,":[76],"mono-script":[80],"collections.":[82],"In":[83],"this":[84],"article,":[85],"we":[86],"present":[87],"a":[88,99],"number":[89],"methods":[91,105],"for":[92,97,117,131,161],"improving":[93],"context":[96],"use":[100,112],"scenario.":[101],"Some":[102],"these":[104],"fact":[107],"improve":[108],"performance":[109],"without":[110],"making":[111],"sentential":[114],"context,":[115],"allowing":[116],"better":[118],"quantification":[119],"degree":[122],"which":[124,137],"particular":[128],"responsible":[130],"system":[132],"improvements.":[133],"Our":[134],"final":[135],"systems,":[136],"ultimately":[138],"rely":[139],"upon":[140],"ensembles":[141],"including":[142],"pretrained":[144],"language":[145],"models":[146],"fine-tuned":[147],"simulated":[149],"data,":[151],"yield":[152],"substantial":[153],"improvements":[154],"over":[155],"best":[157],"previously":[158],"reported":[159],"results":[160],"native":[168],"all":[171],"12":[172],"languages":[173],"Dakshina":[176],"dataset":[177],"(Roark":[178],"et":[179],"al.":[180],"2020),":[181],"with":[182],"an":[183],"overall":[184],"3.3%":[185],"absolute":[186],"(18.6%":[187],"relative)":[188],"mean":[189],"word-error":[190],"rate":[191],"reduction.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}