{"id":"https://openalex.org/W4400528804","doi":"https://doi.org/10.1145/3626772.3657854","title":"Negative Sampling Techniques for Dense Passage Retrieval in a Multilingual Setting","display_name":"Negative Sampling Techniques for Dense Passage Retrieval in a Multilingual Setting","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400528804","doi":"https://doi.org/10.1145/3626772.3657854"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657854","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657854","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051562314","display_name":"Thilina C. Rajapakse","orcid":"https://orcid.org/0000-0001-5482-664X"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thilina Chaturanga Rajapakse","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-5482-664X","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059489981","display_name":"Andrew Yates","orcid":"https://orcid.org/0000-0002-5970-880X"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Andrew Yates","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-5970-880X","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-1086-0202","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4892,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90901722,"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":"575","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9970999956130981,"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":0.7069281339645386},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.555921196937561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41624316573143005},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3565772771835327},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.19103452563285828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069281339645386},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.555921196937561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41624316573143005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3565772771835327},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.19103452563285828},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626772.3657854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657854","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:dare.uva.nl:openaire/9da68804-4197-4dd3-94af-b2ba28a574d7","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/negative-sampling-techniques-for-dense-passage-retrieval-in-a-multilingual-setting(9da68804-4197-4dd3-94af-b2ba28a574d7).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657854","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2069065514","https://openalex.org/W2979826702","https://openalex.org/W2998702515","https://openalex.org/W3021300761","https://openalex.org/W3021397474","https://openalex.org/W3045462440","https://openalex.org/W3082161373","https://openalex.org/W3099700870","https://openalex.org/W3100547398","https://openalex.org/W3155895380","https://openalex.org/W3185042171","https://openalex.org/W3211890822","https://openalex.org/W3212422886","https://openalex.org/W3214364360","https://openalex.org/W4225104598","https://openalex.org/W4252076394","https://openalex.org/W4384639994","https://openalex.org/W4385245566","https://openalex.org/W6600020652"],"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/W4395014643"],"abstract_inverted_index":{"The":[0],"bi-encoder":[1],"transformer":[2],"architecture":[3],"has":[4],"become":[5],"popular":[6],"in":[7,68,75,125],"open-domain":[8],"retrieval,":[9],"surpassing":[10],"traditional":[11],"sparse":[12],"retrieval":[13,101,166],"methods.":[14],"Using":[15],"hard":[16,36,66],"negatives":[17,67,121],"during":[18],"training":[19,94],"can":[20],"improve":[21],"the":[22,40,141,146,160],"effectiveness":[23,41],"of":[24,42,110],"dense":[25,56,104],"retrievers,":[26],"and":[27,53,72,137],"various":[28],"techniques":[29,60,85],"have":[30],"been":[31],"proposed":[32,143],"to":[33,135],"generate":[34],"these":[35,84],"negatives.":[37],"We":[38,58,79,113,149],"investigate":[39],"multiple":[43],"negative":[44,116,155],"sampling":[45,117,156],"methods":[46,50,157],"based":[47,118],"on":[48,99,119,153],"lexical":[49],"(BM25),":[51],"clustering,":[52],"periodically":[54],"updated":[55],"indices.":[57],"examine":[59],"that":[61,86,115],"were":[62],"introduced":[63],"for":[64],"finding":[65,131],"a":[69,76,81,91,107],"monolingual":[70,100],"setting":[71],"reproduce":[73],"them":[74],"multilingual":[77,103,165],"setting.":[78],"discover":[80],"gap":[82],"amongst":[83],"we":[87,97],"fill":[88],"by":[89],"proposing":[90],"novel":[92],"clustered":[93],"method.":[95],"Specifically,":[96],"focus":[98],"using":[102],"retrievers":[105],"across":[106],"broad":[108],"set":[109],"diverse":[111],"languages.":[112],"find":[114],"BM25":[120],"is":[122],"surprisingly":[123],"effective":[124,162],"an":[126],"in-distribution":[127],"setting,":[128],"but":[129],"this":[130],"does":[132],"not":[133],"generalize":[134],"out-of-distribution":[136],"zero-shot":[138],"settings,":[139],"where":[140],"newly":[142],"method":[144],"achieves":[145],"best":[147],"results.":[148],"conclude":[150],"with":[151],"recommendations":[152],"which":[154],"may":[158],"be":[159],"most":[161],"given":[163],"different":[164],"scenarios.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}