{"id":"https://openalex.org/W4285606464","doi":"https://doi.org/10.24963/ijcai.2022/612","title":"Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval","display_name":"Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606464","doi":"https://doi.org/10.24963/ijcai.2022/612"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/612","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/612","pdf_url":"https://www.ijcai.org/proceedings/2022/0612.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0612.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023371171","display_name":"Ning Wu","orcid":"https://orcid.org/0000-0003-0616-3460"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Wu","raw_affiliation_strings":["Microsoft STCA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678419","display_name":"Yaobo Liang","orcid":"https://orcid.org/0000-0002-6595-5145"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaobo Liang","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia {wuning, yalia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia {wuning, yalia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085999236","display_name":"Houxing Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Houxing Ren","raw_affiliation_strings":["Microsoft STCA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077262995","display_name":"Linjun Shou","orcid":"https://orcid.org/0000-0002-1050-7708"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linjun Shou","raw_affiliation_strings":["Microsoft STCA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Duan","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia {wuning, yalia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia {wuning, yalia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072054932","display_name":"Ming Gong","orcid":"https://orcid.org/0000-0002-1584-1211"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ming Gong","raw_affiliation_strings":["Microsoft STCA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060116992","display_name":"Daxin Jiang","orcid":"https://orcid.org/0000-0002-6657-5806"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daxin Jiang","raw_affiliation_strings":["Microsoft STCA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft STCA","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4411","last_page":"4417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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":0.9987999796867371,"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":0.8151270151138306},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7960315346717834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7468454837799072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6620581150054932},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5226918458938599},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49695733189582825},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47237923741340637},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4353598952293396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42855870723724365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3392179608345032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151270151138306},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7960315346717834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7468454837799072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6620581150054932},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5226918458938599},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49695733189582825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47237923741340637},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4353598952293396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42855870723724365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3392179608345032},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/612","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/612","pdf_url":"https://www.ijcai.org/proceedings/2022/0612.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/612","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/612","pdf_url":"https://www.ijcai.org/proceedings/2022/0612.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606464.pdf","grobid_xml":"https://content.openalex.org/works/W4285606464.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2762484717","https://openalex.org/W2798991696","https://openalex.org/W2896457183","https://openalex.org/W2947497897","https://openalex.org/W2951434086","https://openalex.org/W2965373594","https://openalex.org/W2971207485","https://openalex.org/W2973088264","https://openalex.org/W2983040767","https://openalex.org/W2987283559","https://openalex.org/W2989539713","https://openalex.org/W2997339620","https://openalex.org/W3005680577","https://openalex.org/W3007672467","https://openalex.org/W3035390927","https://openalex.org/W3035524453","https://openalex.org/W3036839309","https://openalex.org/W3042711927","https://openalex.org/W3092683697","https://openalex.org/W3099700870","https://openalex.org/W3102483398","https://openalex.org/W3115295967","https://openalex.org/W3118668786","https://openalex.org/W3168875417","https://openalex.org/W3169937871","https://openalex.org/W3171975879","https://openalex.org/W3188983256","https://openalex.org/W3194157311","https://openalex.org/W4297808394","https://openalex.org/W4299574851","https://openalex.org/W4299579390","https://openalex.org/W6757195695","https://openalex.org/W6767737316","https://openalex.org/W6791858558","https://openalex.org/W6863631769","https://openalex.org/W6863994431"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2081900870","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2597655663"],"abstract_inverted_index":{"Recent":[0],"research":[1],"demonstrates":[2],"the":[3,48,136],"effectiveness":[4],"of":[5,50,97],"using":[6,151,194],"pretrained":[7],"language":[8,98],"models":[9,193],"(PLM)":[10],"to":[11,36,92,130],"improve":[12],"dense":[13,17],"retrieval":[14,133,139,171],"and":[15,57,86,104,116,175,187],"multilingual":[16,137],"retrieval.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"present":[23],"a":[24,53,121],"simple":[25],"but":[26,100],"effective":[27,129],"monolingual":[28],"pretraining":[29,192],"task":[30,140],"called":[31],"contrastive":[32,95],"context":[33,55],"prediction":[34],"(CCP)":[35],"learn":[37],"sentence":[38,42,70,124,138],"representation":[39],"by":[40],"modeling":[41],"level":[43],"contextual":[44],"relation.":[45],"By":[46],"pushing":[47,58],"embedding":[49,125],"sentences":[51],"in":[52,72,113,184],"local":[54],"closer":[56],"random":[59],"negative":[60],"samples":[61],"away,":[62],"different":[63,74],"languages":[64,75],"could":[65],"form":[66],"isomorphic":[67],"structure,":[68],"then":[69],"pairs":[71],"two":[73,168,181],"will":[76],"be":[77],"automatically":[78],"aligned.":[79],"Our":[80,154],"experiments":[81],"show":[82],"that":[83],"model":[84,143,155,178],"collapse":[85],"information":[87,117],"leakage":[88],"are":[89],"very":[90,128],"easy":[91],"happen":[93],"during":[94],"training":[96],"model,":[99],"language-specific":[101],"memory":[102],"bank":[103],"asymmetric":[105],"batch":[106],"normalization":[107],"operation":[108],"play":[109],"an":[110],"essential":[111],"role":[112],"preventing":[114],"collapsing":[115],"leakage,":[118],"respectively.":[119],"Besides,":[120],"post-processing":[122],"for":[123],"is":[126],"also":[127,156],"achieve":[131],"better":[132],"performance.":[134],"On":[135,167],"Tatoeba,":[141],"our":[142,177],"achieves":[144,180],"new":[145],"SOTA":[146,182],"results":[147,183],"among":[148,190],"methods":[149],"without":[150],"bilingual":[152,195],"data.":[153,196],"shows":[157],"larger":[158],"gain":[159],"on":[160],"Tatoeba":[161],"when":[162],"transferring":[163],"between":[164],"non-English":[165],"pairs.":[166],"multi-lingual":[169],"query-passage":[170],"tasks,":[172],"XOR":[173],"Retrieve":[174],"Mr.TYDI,":[176],"even":[179],"both":[185],"zero-shot":[186],"supervised":[188],"setting":[189],"all":[191]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}