{"id":"https://openalex.org/W4412377988","doi":"https://doi.org/10.1145/3726302.3730201","title":"Generate-Distill: Training Cross-Language IR Models with Synthetically-Generated Data","display_name":"Generate-Distill: Training Cross-Language IR Models with Synthetically-Generated Data","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377988","doi":"https://doi.org/10.1145/3726302.3730201"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730201","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730201","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730201","source":null,"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"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730201","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037074105","display_name":"Dawn Lawrie","orcid":"https://orcid.org/0000-0001-7347-7086"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210150714","display_name":"Johns Hopkins Hospital","ror":"https://ror.org/05cb1k848","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436","https://openalex.org/I4210150714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Lawrie","raw_affiliation_strings":["Johns Hopkins HLTCOE, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-7347-7086","affiliations":[{"raw_affiliation_string":"Johns Hopkins HLTCOE, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210150714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060057841","display_name":"Efsun Sarioglu Kayi","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210150714","display_name":"Johns Hopkins Hospital","ror":"https://ror.org/05cb1k848","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436","https://openalex.org/I4210150714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Efsun Kayi","raw_affiliation_strings":["Johns Hopkins HLTCOE, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-2357-9807","affiliations":[{"raw_affiliation_string":"Johns Hopkins HLTCOE, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210150714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062016266","display_name":"Eugene Yang","orcid":"https://orcid.org/0000-0002-0051-1535"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210150714","display_name":"Johns Hopkins Hospital","ror":"https://ror.org/05cb1k848","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436","https://openalex.org/I4210150714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Yang","raw_affiliation_strings":["Johns Hopkins HLTCOE, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-0051-1535","affiliations":[{"raw_affiliation_string":"Johns Hopkins HLTCOE, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210150714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036270568","display_name":"James Mayfield","orcid":"https://orcid.org/0000-0003-3866-3013"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210150714","display_name":"Johns Hopkins Hospital","ror":"https://ror.org/05cb1k848","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436","https://openalex.org/I4210150714"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Mayfield","raw_affiliation_strings":["Johns Hopkins HLTCOE, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-3866-3013","affiliations":[{"raw_affiliation_string":"Johns Hopkins HLTCOE, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210150714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074322406","display_name":"Douglas W. Oard","orcid":"https://orcid.org/0000-0002-1696-0407"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas W. Oard","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-1696-0407","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051632259","display_name":"S.L. Miller","orcid":"https://orcid.org/0009-0003-3345-6346"},"institutions":[{"id":"https://openalex.org/I1309400984","display_name":"Boston Biomedical Research Institute","ror":"https://ror.org/04rqpth59","country_code":"US","type":"facility","lineage":["https://openalex.org/I1309400984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Miller","raw_affiliation_strings":["USC Information Sciences Institute, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0009-0003-3345-6346","affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I1309400984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9201275,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2926","last_page":"2930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9700000286102295,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9559999704360962,"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/computer-science","display_name":"Computer science","score":0.7514221668243408},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5869554877281189},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5734061598777771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5330440402030945},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.531313419342041},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42986685037612915},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3949199616909027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7514221668243408},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5869554877281189},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5734061598777771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5330440402030945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.531313419342041},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42986685037612915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3949199616909027},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730201","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730201","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730201","source":null,"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"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730201","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730201","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730201","source":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377988.pdf","grobid_xml":"https://content.openalex.org/works/W4412377988.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W134702066","https://openalex.org/W2069065514","https://openalex.org/W2945127593","https://openalex.org/W3021397474","https://openalex.org/W3034945650","https://openalex.org/W3035390927","https://openalex.org/W3099446234","https://openalex.org/W3099700870","https://openalex.org/W3169483174","https://openalex.org/W4306317212","https://openalex.org/W4365799947","https://openalex.org/W4384648820","https://openalex.org/W4385573019","https://openalex.org/W4387846439","https://openalex.org/W4387848569","https://openalex.org/W4392575810","https://openalex.org/W4392869958","https://openalex.org/W4400528444","https://openalex.org/W4401043161","https://openalex.org/W4406942015","https://openalex.org/W6607721473"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4394050964","https://openalex.org/W2551249631","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Most":[0],"pretrained":[1],"language":[2,91],"models":[3],"that":[4,39,81],"support":[5],"neural":[6],"information":[7],"retrieval":[8,83],"are":[9],"fine-tuned":[10],"on":[11,110],"the":[12,41,44,47,74,103,125],"MS":[13,67,131],"MARCO":[14,16,68,132],"dataset.MS":[15],"is":[17,85,107],"expressed":[18],"in":[19,102],"English,":[20],"so":[21],"it":[22],"naturally":[23,37],"supports":[24],"monolingual":[25],"English":[26,62],"retrieval.However,":[27],"for":[28,94],"Cross-Language":[29],"Information":[30],"Retrieval":[31],"(CLIR),":[32],"no":[33],"similar":[34],"training":[35,128],"data":[36],"exists":[38],"matches":[40],"languages":[42],"of":[43,127],"query":[45,104],"and":[46,113],"documents.The":[48],"main":[49],"ways":[50],"to":[51,57,59,65,72,88,98,108,123],"address":[52],"this":[53,117],"problem":[54],"have":[55],"been":[56],"continue":[58],"fine-tune":[60],"with":[61,119,129],"data,":[63],"or":[64],"translate":[66],"queries":[69,101],"and/or":[70],"documents":[71,92,112],"match":[73,124],"CLIR":[75],"setting.Machine":[76],"translation":[77],"often":[78],"introduces":[79],"errors":[80],"reduce":[82],"effectiveness.It":[84],"usually":[86],"easy":[87],"find":[89,99],"target":[90],"suitable":[93],"training,":[95],"but":[96],"difficult":[97],"naturally-occurring":[100,111],"language.An":[105],"alternative":[106],"train":[109],"syntheticallygenerated":[114],"queries.Generate-Distill":[115],"uses":[116],"approach":[118],"stateof-the-art":[120],"distillation":[121],"methods":[122],"effectiveness":[126],"translated":[130],"across":[133],"different":[134],"domains.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}