{"id":"https://openalex.org/W4385780698","doi":"https://doi.org/10.1145/3613447","title":"Toward Best Practices for Training Multilingual Dense Retrieval Models","display_name":"Toward Best Practices for Training Multilingual Dense Retrieval Models","publication_year":2023,"publication_date":"2023-08-12","ids":{"openalex":"https://openalex.org/W4385780698","doi":"https://doi.org/10.1145/3613447"},"language":"en","primary_location":{"id":"doi:10.1145/3613447","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613447","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613447","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613447","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100390744","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0009-0009-0756-8110"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088147173","display_name":"Kelechi Ogueji","orcid":"https://orcid.org/0009-0004-7919-9303"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kelechi Ogueji","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021623012","display_name":"Xueguang Ma","orcid":"https://orcid.org/0000-0003-3430-4910"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xueguang Ma","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100390744"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":2.0739,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8954698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"42","issue":"2","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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":0.8755669593811035},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7302344441413879},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5460323691368103},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5409286022186279},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5281472206115723},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5166426301002502},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5125658512115479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4749617278575897},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4641742706298828},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45242631435394287},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4216618239879608},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4101761281490326},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36918628215789795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755669593811035},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7302344441413879},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5460323691368103},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5409286022186279},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5281472206115723},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5166426301002502},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5125658512115479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749617278575897},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4641742706298828},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45242631435394287},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4216618239879608},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4101761281490326},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36918628215789795},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613447","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613447","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613447","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3613447","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613447","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613447","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320326644","display_name":"Canada First Research Excellence Fund","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385780698.pdf","grobid_xml":"https://content.openalex.org/works/W4385780698.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W336359994","https://openalex.org/W1821462560","https://openalex.org/W2148437670","https://openalex.org/W2241862190","https://openalex.org/W2489487449","https://openalex.org/W2750779823","https://openalex.org/W2912924812","https://openalex.org/W2950315151","https://openalex.org/W2951534261","https://openalex.org/W2952638691","https://openalex.org/W2970925270","https://openalex.org/W2981852735","https://openalex.org/W2982596739","https://openalex.org/W2986154550","https://openalex.org/W2998702515","https://openalex.org/W3011663485","https://openalex.org/W3034238904","https://openalex.org/W3034469191","https://openalex.org/W3035390927","https://openalex.org/W3035547806","https://openalex.org/W3092302355","https://openalex.org/W3093517588","https://openalex.org/W3101118213","https://openalex.org/W3103187652","https://openalex.org/W3115195983","https://openalex.org/W3136120753","https://openalex.org/W3154670582","https://openalex.org/W3164045210","https://openalex.org/W3166441238","https://openalex.org/W3175567752","https://openalex.org/W3198713493","https://openalex.org/W3200910169","https://openalex.org/W3213418658","https://openalex.org/W4205103289","https://openalex.org/W4205185581","https://openalex.org/W4205293907","https://openalex.org/W4205480697","https://openalex.org/W4205807230","https://openalex.org/W4206277161","https://openalex.org/W4210976132","https://openalex.org/W4212774754","https://openalex.org/W4213069590","https://openalex.org/W4239019441","https://openalex.org/W4242973245","https://openalex.org/W4284664419","https://openalex.org/W4286969177","https://openalex.org/W4287018294","https://openalex.org/W4287645694","https://openalex.org/W4287827771","https://openalex.org/W4287993739","https://openalex.org/W4288089799","https://openalex.org/W4291238844","https://openalex.org/W4300427681","https://openalex.org/W4306891354","https://openalex.org/W4309453583","https://openalex.org/W4320813768","https://openalex.org/W4322760792","https://openalex.org/W4362598841","https://openalex.org/W6638523607","https://openalex.org/W6758015726","https://openalex.org/W6769185743","https://openalex.org/W6771823989","https://openalex.org/W6850697714"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Dense":[0],"retrieval":[1,26,75],"models":[2,114,132],"using":[3,34],"a":[4,28,67,84,143,176,193,200],"transformer-based":[5],"bi-encoder":[6],"architecture":[7],"have":[8],"emerged":[9],"as":[10,66],"an":[11,36],"active":[12],"area":[13],"of":[14,24,30,95,106,146,149,154,162,168,195],"research.":[15],"In":[16,137],"this":[17],"article,":[18],"we":[19,59,141,198],"focus":[20],"on":[21],"the":[22,93,102,147,152,160,166],"task":[23],"monolingual":[25,171],"in":[27,92,101],"variety":[29],"typologically":[31],"diverse":[32],"languages":[33],"such":[35],"architecture.":[37],"Although":[38],"recent":[39],"work":[40,190],"with":[41],"multilingual":[42,73,85,169],"transformers":[43],"demonstrates":[44],"that":[45],"they":[46],"exhibit":[47],"strong":[48],"cross-lingual":[49,155],"generalization":[50],"capabilities,":[51],"there":[52],"remain":[53],"many":[54],"open":[55,192],"research":[56,196],"questions,":[57,197],"which":[58],"tackle":[60],"here.":[61],"Our":[62,173],"study":[63],"is":[64,87],"organized":[65],"\u201cbest":[68],"practices\u201d":[69],"guide":[70,177],"for":[71,178,184,203],"training":[72,90,116,126],"dense":[74],"models,":[76],"broken":[77],"down":[78],"into":[79],"three":[80],"main":[81],"scenarios:":[82],"when":[83,112,125],"transformer":[86],"available,":[88],"but":[89,130],"data":[91,117,127],"form":[94],"relevance":[96],"judgments":[97],"are":[98,118,128],"not":[99,131],"available":[100,119,129],"language":[103],"and":[104,115,122,124,165,187],"domain":[105],"interest":[107],"(\u201chave":[108,120,133],"model,":[109],"no":[110,135],"data\u201d);":[111,123],"both":[113],"model":[121],"data,":[134,164],"model\u201d).":[136],"considering":[138],"these":[139],"scenarios,":[140],"gain":[142],"better":[144],"understanding":[145],"role":[148],"multi-stage":[150],"fine-tuning,":[151],"strength":[153],"transfer":[156],"under":[157],"various":[158],"conditions,":[159],"usefulness":[161],"out-of-language":[163],"advantages":[167],"vs.":[170],"transformers.":[172],"recommendations":[174],"offer":[175],"practitioners":[179],"building":[180],"search":[181],"applications,":[182],"particularly":[183],"low-resource":[185],"languages,":[186],"while":[188],"our":[189],"leaves":[191],"number":[194],"provide":[199],"solid":[201],"foundation":[202],"future":[204],"work.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}