{"id":"https://openalex.org/W4318718892","doi":"https://doi.org/10.1145/3539597.3570468","title":"Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation","display_name":"Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4318718892","doi":"https://doi.org/10.1145/3539597.3570468"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570468","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539597.3570468","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570468","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076939668","display_name":"Zhiqi Huang","orcid":"https://orcid.org/0000-0002-2939-1936"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqi Huang","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2939-1936","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090488104","display_name":"Puxuan Yu","orcid":"https://orcid.org/0000-0001-7913-8632"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puxuan Yu","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7913-8632","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034070218","display_name":"James Allan","orcid":"https://orcid.org/0000-0003-0132-5694"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Allan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0132-5694","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":5.8665,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97069955,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1048","last_page":"1056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.9975000023841858,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9958000183105469,"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/T12029","display_name":"DNA and Biological Computing","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7020377516746521},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.666968047618866},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5544763207435608},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46770355105400085},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4423767626285553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36331266164779663},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.117642343044281},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08636122941970825},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08231627941131592}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020377516746521},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.666968047618866},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5544763207435608},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46770355105400085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4423767626285553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36331266164779663},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.117642343044281},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08636122941970825},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08231627941131592}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539597.3570468","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539597.3570468","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570468","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.12566","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.12566","pdf_url":"https://arxiv.org/pdf/2301.12566","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:10.1145/3539597.3570468","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539597.3570468","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570468","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1270017660","display_name":null,"funder_award_id":"2019-19051600007","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G2261877036","display_name":null,"funder_award_id":"2019-19051600007","funder_id":"https://openalex.org/F4320312530","funder_display_name":"Office of the Director of National Intelligence"}],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318718892.pdf","grobid_xml":"https://content.openalex.org/works/W4318718892.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1594039573","https://openalex.org/W1821462560","https://openalex.org/W2068297964","https://openalex.org/W2158131535","https://openalex.org/W2187089797","https://openalex.org/W2536015822","https://openalex.org/W2803620078","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2913077324","https://openalex.org/W2951534261","https://openalex.org/W2952851926","https://openalex.org/W2954573505","https://openalex.org/W2963617771","https://openalex.org/W2964343359","https://openalex.org/W2966645965","https://openalex.org/W2976672264","https://openalex.org/W2978017171","https://openalex.org/W2987809065","https://openalex.org/W2988809116","https://openalex.org/W3021397474","https://openalex.org/W3032608552","https://openalex.org/W3034368386","https://openalex.org/W3034439313","https://openalex.org/W3034724424","https://openalex.org/W3035160371","https://openalex.org/W3035390927","https://openalex.org/W3035473397","https://openalex.org/W3035540729","https://openalex.org/W3038047279","https://openalex.org/W3082928416","https://openalex.org/W3094444847","https://openalex.org/W3098366475","https://openalex.org/W3098466758","https://openalex.org/W3100806282","https://openalex.org/W3105425516","https://openalex.org/W3138154797","https://openalex.org/W3154079701","https://openalex.org/W3197002404","https://openalex.org/W3200538116","https://openalex.org/W4212764525","https://openalex.org/W4213224406","https://openalex.org/W4224947540","https://openalex.org/W4225565111","https://openalex.org/W4225727172","https://openalex.org/W4226112939","https://openalex.org/W4281489207","https://openalex.org/W4283802945","https://openalex.org/W4287018294","https://openalex.org/W4287645694","https://openalex.org/W4288629163","https://openalex.org/W4297708031"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W32245304","https://openalex.org/W2953684491","https://openalex.org/W4285338581","https://openalex.org/W2768175398","https://openalex.org/W2015158429","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Benefiting":[0],"from":[1,133,153,164],"transformer-based":[2],"pre-trained":[3,19,65],"language":[4,20,41,69,105],"models,":[5],"neural":[6,27,202],"ranking":[7,90],"models":[8,21,42,61,66],"have":[9,43],"made":[10],"significant":[11],"progress.":[12],"More":[13],"recently,":[14],"the":[15,80,97,141,161],"advent":[16],"of":[17,99,166],"multilingual":[18,40],"provides":[22],"great":[23],"support":[24],"for":[25,75,88,103,110,124,175,182],"designing":[26],"cross-lingual":[28,59,100,112,162],"retrieval":[29,60,82,101,113,157],"models.":[30,114],"However,":[31],"due":[32],"to":[33,72,135,151],"unbalanced":[34],"pre-training":[35],"data":[36,102,174],"in":[37,54],"different":[38],"languages,":[39,138,200],"already":[44],"shown":[45],"a":[46,131,154],"performance":[47],"gap":[48],"between":[49],"high":[50,134],"and":[51],"low-resource":[52,76,104,125,183,199],"languages":[53],"many":[55],"downstream":[56],"tasks.":[57],"And":[58],"built":[62],"on":[63,198],"such":[64,91],"can":[67],"inherit":[68],"bias,":[70],"leading":[71],"suboptimal":[73],"result":[74],"languages.":[77,184],"Moreover,":[78],"unlike":[79],"English-to-English":[81],"task,":[83],"where":[84],"large-scale":[85],"training":[86,111,191],"collections":[87],"document":[89,168],"as":[92,146],"MS":[93],"MARCO":[94],"are":[95],"available,":[96],"lack":[98],"makes":[106],"it":[107],"more":[108,180],"challenging":[109],"In":[115],"this":[116],"work,":[117],"we":[118],"propose":[119],"OPTICAL:":[120],"<u>Op</u>timal":[121],"<u>T</u>ransport":[122],"dist<u>i</u>llation":[123],"<u>C</u>ross-lingual":[126],"information":[127],"retrieval.":[128],"To":[129],"transfer":[130],"model":[132],"low":[136],"resource":[137],"OPTICAL":[139,170,193],"forms":[140],"cross-lingu<u>al</u>":[142],"token":[143],"alignment":[144],"task":[145],"an":[147],"optimal":[148],"transport":[149],"problem":[150],"learn":[152],"well-trained":[155],"monolingual":[156],"model.":[158],"By":[159],"separating":[160],"knowledge":[163,165],"query":[167],"matching,":[169],"only":[171],"needs":[172],"bitext":[173],"distillation":[176],"training,":[177],"which":[178],"is":[179],"feasible":[181],"Experimental":[185],"results":[186],"show":[187],"that,":[188],"with":[189],"minimal":[190],"data,":[192],"significantly":[194],"outperforms":[195],"strong":[196],"baselines":[197],"including":[201],"machine":[203],"translation.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2023-02-01T00:00:00"}