{"id":"https://openalex.org/W7126408414","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.49","title":"Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling","display_name":"Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126408414","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.49"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.49","pdf_url":"https://aclanthology.org/2024.findings-eacl.49.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.49.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124560556","display_name":"Chao-Wei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao-Wei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124554695","display_name":"Chen-An Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen-An Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124510546","display_name":"Tsu-Yuan Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsu-Yuan Hsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551098","display_name":"Chen-Yu Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen-Yu Hsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124558081","display_name":"Yun-Nung Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun-Nung Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70257692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.3531000018119812,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.3531000018119812,"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":0.21580000221729279,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.1354999989271164,"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/feature","display_name":"Feature (linguistics)","score":0.3882000148296356},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3684000074863434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3441999852657318},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3215999901294708},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.26809999346733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6644999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6430000066757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.49","pdf_url":"https://aclanthology.org/2024.findings-eacl.49.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.49","pdf_url":"https://aclanthology.org/2024.findings-eacl.49.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126408414.pdf","grobid_xml":"https://content.openalex.org/works/W7126408414.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"retrieval":[1],"methods":[2],"have":[3],"demonstrated":[4],"promising":[5],"performance":[6,78],"in":[7,17,35],"multilingual":[8,36,59,80,99],"information":[9],"retrieval,":[10],"where":[11],"queries":[12],"and":[13],"documents":[14],"can":[15],"be":[16],"different":[18],"languages.However,":[19],"dense":[20,44,68,81],"retrievers":[21,100],"typically":[22],"require":[23],"a":[24,71],"substantial":[25],"amount":[26],"of":[27,58,79,97],"paired":[28,49,102],"data,":[29,103],"which":[30,74],"poses":[31],"even":[32],"greater":[33],"challenges":[34],"scenarios.This":[37],"paper":[38],"introduces":[39],"UMR,":[40],"an":[41],"Unsupervised":[42],"Multilingual":[43],"Retriever":[45],"trained":[46],"without":[47,101],"any":[48],"data.Our":[50],"approach":[51],"leverages":[52],"the":[53,77,95],"sequence":[54],"likelihood":[55],"estimation":[56],"capabilities":[57],"language":[60],"models":[61],"to":[62],"acquire":[63],"pseudo":[64],"labels":[65],"for":[66],"training":[67,98],"retrievers.We":[69],"propose":[70],"two-stage":[72],"framework":[73],"iteratively":[75],"improves":[76],"retrievers.Experimental":[82],"results":[83],"on":[84],"two":[85],"benchmark":[86],"datasets":[87],"show":[88],"that":[89],"UMR":[90],"outperforms":[91],"supervised":[92],"baselines,":[93],"showcasing":[94],"potential":[96],"thereby":[104],"enhancing":[105],"their":[106],"practicality.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}