{"id":"https://openalex.org/W4412378006","doi":"https://doi.org/10.1145/3726302.3730226","title":"Lost in Transliteration: Bridging the Script Gap in Neural IR","display_name":"Lost in Transliteration: Bridging the Script Gap in Neural IR","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412378006","doi":"https://doi.org/10.1145/3726302.3730226"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730226","doi":"https://doi.org/10.1145/3726302.3730226","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730226","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730226","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730226","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034735341","display_name":"Andreas Chari","orcid":"https://orcid.org/0009-0007-9246-8207","observed_orcids":["https://orcid.org/0009-0007-9246-8207"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andreas Chari","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0007-9246-8207","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223","observed_orcids":["https://orcid.org/0000-0003-4701-3223"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4701-3223","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199889","display_name":"Sean MacAvaney","orcid":"https://orcid.org/0000-0002-8914-2659","observed_orcids":["https://orcid.org/0000-0002-8914-2659"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sean MacAvaney","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8914-2659","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":4.7086,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95310489,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2900","last_page":"2905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9965999722480774,"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":0.9965999722480774,"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":0.002400000113993883,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00019999999494757503,"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/transliteration","display_name":"transliteration","score":0.9700000286102295},{"id":"https://openalex.org/keywords/multilingual-information-retrieval","display_name":"multilingual information retrieval","score":0.7839999794960022},{"id":"https://openalex.org/keywords/neural-retrieval","display_name":"neural retrieval","score":0.777999997138977},{"id":"https://openalex.org/keywords/dense-embeddings","display_name":"dense embeddings","score":0.4779999852180481},{"id":"https://openalex.org/keywords/bge-m3","display_name":"BGE-M3","score":0.8600000143051147},{"id":"https://openalex.org/keywords/arabizi","display_name":"Arabizi","score":0.9890000224113464},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9060856103897095},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8503048419952393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6451786756515503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48530691862106323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781419038772583},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07751297950744629}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730226","doi":"https://doi.org/10.1145/3726302.3730226","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730226","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730226","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:352746","doi":null,"is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/68265.html>,","pdf_url":"https://eprints.gla.ac.uk/352746/2/352746.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730226","doi":"https://doi.org/10.1145/3726302.3730226","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730226","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730226","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412378006.pdf","grobid_xml":"https://content.openalex.org/works/W4412378006.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1987886907","https://openalex.org/W2068130800","https://openalex.org/W2165990829","https://openalex.org/W2479127134","https://openalex.org/W2804732445","https://openalex.org/W2805866690","https://openalex.org/W2981852735","https://openalex.org/W2983040767","https://openalex.org/W3045745713","https://openalex.org/W3104914963","https://openalex.org/W3133594109","https://openalex.org/W3156166379","https://openalex.org/W3169483174","https://openalex.org/W3217485291","https://openalex.org/W4226112939","https://openalex.org/W4288089799","https://openalex.org/W4327644092","https://openalex.org/W4366492380","https://openalex.org/W4367060421","https://openalex.org/W4384660938","https://openalex.org/W4394838713","https://openalex.org/W4402670856","https://openalex.org/W4402671194","https://openalex.org/W4402671848","https://openalex.org/W4416034459"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3153459181","https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W2371976984","https://openalex.org/W2352160949","https://openalex.org/W2069398544","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Most":[0],"human":[1],"languages":[2,14],"use":[3,35,41,53],"scripts":[4],"other":[5],"than":[6],"the":[7,82,85,100,108,118,144,185,190,195],"Latin":[8],"alphabet.":[9],"Search":[10],"users":[11],"in":[12,20,90,194],"these":[13],"often":[15],"formulate":[16],"their":[17,67,91,215],"information":[18],"needs":[19],"a":[21,78],"transliterated":[22,74,94,123],"-usually":[23],"Latinized-":[24],"form":[25],"for":[26,136],"ease":[27],"of":[28,84,110,130,146,172,214],"typing.":[29],"For":[30],"example,":[31],"Greek":[32],"speakers":[33,39],"might":[34,40],"Greeklish,":[36],"and":[37,66,116,122,132,151,174,200],"Arabic":[38],"Arabizi.":[42],"This":[43,76],"paper":[44],"shows":[45],"that":[46,52,162,205],"current":[47],"search":[48],"systems,":[49],"including":[50],"those":[51],"multilingual":[54,111],"dense":[55],"embeddings":[56],"such":[57],"as":[58,188],"BGE-M3,":[59],"do":[60],"not":[61],"generalise":[62],"to":[63,73,104,154,156,211],"this":[64,157,180],"setting,":[65],"performance":[68,83,187],"rapidly":[69],"deteriorates":[70],"when":[71,88,189],"exposed":[72],"queries.":[75],"creates":[77],"''script":[79],"gap''":[80],"between":[81,120],"same":[86,186],"queries":[87,210],"written":[89],"native":[92,121,173,196],"or":[93],"form.":[95],"We":[96,160],"explore":[97],"whether":[98,140],"adapting":[99],"popular":[101],"''translate-train''":[102],"paradigm":[103],"transliterations":[105,206],"can":[106,142,178,207],"enhance":[107,143],"robustness":[109],"Information":[112],"Retrieval":[113],"(IR)":[114],"methods":[115],"bridge":[117],"gap":[119],"scripts.":[124],"https://github.com/andreaschari/transliterations":[125],"By":[126],"exploring":[127],"various":[128],"combinations":[129],"non-Latin":[131],"Latinized":[133,175],"query":[134,191],"text":[135],"training,":[137],"we":[138,141],"investigate":[139],"capacity":[145],"existing":[147],"neural":[148],"retrieval":[149],"techniques":[150],"enable":[152],"them":[153],"apply":[155],"important":[158],"setting.":[159],"show":[161,204],"by":[163],"further":[164,201,218],"fine-tuning":[165],"IR":[166],"models":[167],"on":[168],"an":[169],"even":[170],"mixture":[171],"text,":[176],"they":[177],"perform":[179],"cross-script":[181],"matching":[182],"at":[183],"nearly":[184],"was":[192],"formulated":[193],"script.":[197],"Out-of-domain":[198],"evaluation":[199],"qualitative":[202],"analysis":[203],"also":[208],"cause":[209],"lose":[212],"some":[213],"nuances,":[216],"motivating":[217],"research.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}