{"id":"https://openalex.org/W4396812194","doi":"https://doi.org/10.1145/3626772.3657955","title":"Distillation for Multilingual Information Retrieval","display_name":"Distillation for Multilingual Information Retrieval","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4396812194","doi":"https://doi.org/10.1145/3626772.3657955"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657955","pdf_url":null,"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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Yang","raw_affiliation_strings":["HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0002-0051-1535","affiliations":[{"raw_affiliation_string":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Lawrie","raw_affiliation_strings":["HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0001-7347-7086","affiliations":[{"raw_affiliation_string":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Mayfield","raw_affiliation_strings":["HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0003-3866-3013","affiliations":[{"raw_affiliation_string":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.5776,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87182685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2368","last_page":"2373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9976999759674072,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.759419322013855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6429136395454407},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.533247709274292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3839952051639557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35761529207229614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759419322013855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6429136395454407},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.533247709274292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3839952051639557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35761529207229614},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626772.3657955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657955","pdf_url":null,"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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.00977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.00977","pdf_url":"https://arxiv.org/pdf/2405.00977","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657955","pdf_url":null,"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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W208683199","https://openalex.org/W793561756","https://openalex.org/W1573481780","https://openalex.org/W2014064503","https://openalex.org/W2037698344","https://openalex.org/W2044157185","https://openalex.org/W2046456023","https://openalex.org/W2056989505","https://openalex.org/W2069065514","https://openalex.org/W2089130131","https://openalex.org/W2089379373","https://openalex.org/W2124509324","https://openalex.org/W2168801328","https://openalex.org/W2595551253","https://openalex.org/W2610765860","https://openalex.org/W2911319979","https://openalex.org/W2945127593","https://openalex.org/W2963469388","https://openalex.org/W2998702515","https://openalex.org/W3021397474","https://openalex.org/W3035390927","https://openalex.org/W3099446234","https://openalex.org/W3100107515","https://openalex.org/W3154280800","https://openalex.org/W3188983256","https://openalex.org/W3212963155","https://openalex.org/W3217305727","https://openalex.org/W4205103289","https://openalex.org/W4221150501","https://openalex.org/W4224983763","https://openalex.org/W4225727172","https://openalex.org/W4239019441","https://openalex.org/W4327644092","https://openalex.org/W4376123230","https://openalex.org/W4392869958","https://openalex.org/W6607721473","https://openalex.org/W6831594568"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"work":[1,72],"in":[2,12,68,108,114,130],"cross-language":[3,26],"information":[4,43],"retrieval":[5,44],"(CLIR),":[6],"where":[7],"queries":[8],"and":[9,32,75,110],"documents":[10,67],"are":[11,128],"different":[13,69],"languages,":[14],"has":[15],"shown":[16],"the":[17,20,59,99,120,125],"benefit":[18],"of":[19],"Translate-Distill":[21,35,74,78],"framework":[22],"that":[23,84,119],"trains":[24],"a":[25,38,48],"neural":[27],"dual-encoder":[28],"model":[29,60,121],"using":[30],"translation":[31],"distillation.":[33],"However,":[34],"only":[36],"supports":[37],"single":[39],"document":[40,50],"language.":[41],"Multilingual":[42,77,95],"(MLIR),":[45],"which":[46,97],"ranks":[47],"multilingual":[49],"collection,":[51],"is":[52,98,122,135],"harder":[53],"to":[54,66,106,112,124],"train":[55],"than":[56],"CLIR":[57],"because":[58],"must":[61],"assign":[62],"comparable":[63],"relevance":[64],"scores":[65],"languages.":[70],"This":[71],"extends":[73],"propose":[76],"(MTD)":[79],"for":[80],"MLIR.":[81],"We":[82,116],"show":[83,118],"ColBERT-X":[85],"models":[86],"trained":[87,93],"with":[88,94],"MTD":[89],"outperform":[90],"their":[91],"counterparts":[92],"Translate-Train,":[96],"previous":[100],"state-of-the-art":[101],"training":[102,131],"approach,":[103],"by":[104],"5%":[105],"25%":[107],"nDCG@20":[109],"15%":[111],"45%":[113],"MAP.":[115],"also":[117],"robust":[123],"way":[126],"languages":[127],"mixed":[129],"batches.":[132],"Our":[133],"implementation":[134],"available":[136],"on":[137],"GitHub.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}