{"id":"https://openalex.org/W4384639994","doi":"https://doi.org/10.1145/3539618.3591915","title":"Balanced Topic Aware Sampling for Effective Dense Retriever: A Reproducibility Study","display_name":"Balanced Topic Aware Sampling for Effective Dense Retriever: A Reproducibility Study","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384639994","doi":"https://doi.org/10.1145/3539618.3591915"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100328263","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0726-5250"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100328263"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":1.1764,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81043632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2542","last_page":"2551"},"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":0.998199999332428,"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":0.9940999746322632,"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/boosting","display_name":"Boosting (machine learning)","score":0.791630744934082},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7373369932174683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355939745903015},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5389121174812317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.530326783657074},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.517753541469574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5100985169410706},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4846423268318176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33586227893829346},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08133944869041443},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07179170846939087}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.791630744934082},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7373369932174683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355939745903015},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5389121174812317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.530326783657074},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.517753541469574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5100985169410706},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4846423268318176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33586227893829346},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08133944869041443},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07179170846939087},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4269867787","display_name":null,"funder_award_id":"DP210104043","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2115584760","https://openalex.org/W3034368386","https://openalex.org/W3035404611","https://openalex.org/W3138154797","https://openalex.org/W3154670582","https://openalex.org/W3175111331","https://openalex.org/W3180230246","https://openalex.org/W3198431451","https://openalex.org/W4225372933"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2487162673","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W2793211469","https://openalex.org/W1489772951","https://openalex.org/W2949152769"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1,40],"plays":[2],"a":[3,30,42],"key":[4],"role":[5],"in":[6,62],"boosting":[7],"the":[8,36,47,63,66,79,84,88],"effectiveness":[9],"of":[10,38,65,76,87],"rankers":[11],"based":[12],"on":[13],"pre-trained":[14],"language":[15],"models":[16],"(PLMs);":[17],"this":[18],"is":[19],"achieved":[20],"using":[21],"an":[22],"effective":[23],"but":[24],"inefficient":[25],"large":[26],"model":[27],"to":[28,55],"teach":[29],"more":[31],"efficient":[32],"student":[33,43],"model.":[34],"In":[35],"context":[37],"knowledge":[39],"for":[41],"dense":[44],"passage":[45],"retriever,":[46],"balanced":[48],"topic-aware":[49],"sampling":[50],"method":[51,60],"has":[52],"been":[53],"shown":[54],"provide":[56],"state-of-the-art":[57],"effectiveness.":[58],"This":[59],"intervenes":[61],"creation":[64],"training":[67],"batches":[68,71],"by":[69],"creating":[70],"that":[72],"contain":[73],"positive-negative":[74],"pairs":[75],"passages":[77],"from":[78],"same":[80],"topic,":[81],"and":[82,90],"balancing":[83],"pairwise":[85],"margins":[86],"positive":[89],"negative":[91],"passages.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}