{"id":"https://openalex.org/W4413168954","doi":"https://doi.org/10.1186/s40537-025-01257-9","title":"Data augmentation for dense passage retrieval using corpus-passage frequency-based token deletion","display_name":"Data augmentation for dense passage retrieval using corpus-passage frequency-based token deletion","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W4413168954","doi":"https://doi.org/10.1186/s40537-025-01257-9"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-025-01257-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01257-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s40537-025-01257-9.pdf","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s40537-025-01257-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084068555","display_name":"A-Seong Moon","orcid":"https://orcid.org/0000-0001-9880-1401"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"A-Seong Moon","raw_affiliation_strings":["Deparment of Artificial Intelligence, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Deparment of Artificial Intelligence, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101721499","display_name":"Kyumin Kim","orcid":"https://orcid.org/0000-0002-6242-3629"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyumin Kim","raw_affiliation_strings":["Deparment of Artificial Intelligence, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Deparment of Artificial Intelligence, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108076719","display_name":"Jaesung Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaesung Lee","raw_affiliation_strings":["AI/ML Innovation Research Center, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea","Deparment of Artificial Intelligence, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"AI/ML Innovation Research Center, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Deparment of Artificial Intelligence, Chung-Ang University, 84, Heukseok-ro, Dongjak-gu, Seoul, 06911, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108076719"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10178696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8634437322616577},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7719045877456665},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.5694116950035095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45258814096450806},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37084466218948364},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32369109988212585},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16529366374015808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15533632040023804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8634437322616577},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7719045877456665},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.5694116950035095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45258814096450806},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37084466218948364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32369109988212585},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16529366374015808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15533632040023804}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-025-01257-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01257-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s40537-025-01257-9.pdf","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cae1d25d4ba642ed81522114b2a46462","is_oa":true,"landing_page_url":"https://doaj.org/article/cae1d25d4ba642ed81522114b2a46462","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 12, Iss 1, Pp 1-28 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-025-01257-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01257-9","pdf_url":"https://link.springer.com/content/pdf/10.1186/s40537-025-01257-9.pdf","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G13572568","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8500822167","display_name":null,"funder_award_id":"2021-0- 01341-003","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321202","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413168954.pdf","grobid_xml":"https://content.openalex.org/works/W4413168954.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2051167396","https://openalex.org/W2118978333","https://openalex.org/W2194775991","https://openalex.org/W2251818205","https://openalex.org/W2946417913","https://openalex.org/W2951434086","https://openalex.org/W2962854673","https://openalex.org/W2962910668","https://openalex.org/W2962985038","https://openalex.org/W2963216553","https://openalex.org/W2963469388","https://openalex.org/W2970482702","https://openalex.org/W2971105107","https://openalex.org/W2971296908","https://openalex.org/W2972324944","https://openalex.org/W3097513514","https://openalex.org/W3099700870","https://openalex.org/W3154280800","https://openalex.org/W3157758108","https://openalex.org/W3168875417","https://openalex.org/W3172119680","https://openalex.org/W3174367567","https://openalex.org/W3174828871","https://openalex.org/W3176923149","https://openalex.org/W3196750896","https://openalex.org/W3206995700","https://openalex.org/W4206660322","https://openalex.org/W4252076394","https://openalex.org/W4381686872","https://openalex.org/W4385570822","https://openalex.org/W4385571915","https://openalex.org/W4385573139","https://openalex.org/W4385574018","https://openalex.org/W4389524221","https://openalex.org/W4402671923","https://openalex.org/W4404780784","https://openalex.org/W6600103761","https://openalex.org/W6765507828"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4285141722","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,117],"paper":[1],"proposes":[2],"a":[3,19,37],"novel":[4],"data":[5,112],"augmentation":[6,91],"method":[7,57],"to":[8,27,69,89,121],"address":[9],"class":[10,115],"imbalance":[11],"in":[12,106],"large-scale":[13],"information":[14,40,126],"retrieval":[15,41,127],"systems.":[16],"In":[17],"particular,":[18],"corpus-passage":[20],"frequency-based":[21],"token":[22,46,59,72],"deletion":[23,47],"technique":[24],"is":[25,36,103,132],"introduced":[26],"improve":[28,122],"the":[29,55,78,123],"accuracy":[30,84],"of":[31,125],"Dense":[32],"Passage":[33],"Retrieval,":[34],"which":[35],"dense":[38],"vector-based":[39],"model.":[42],"Unlike":[43],"traditional":[44],"random":[45],"methods":[48],"that":[49,77],"delete":[50],"tokens":[51],"with":[52],"equal":[53],"probability,":[54],"proposed":[56,79],"calculates":[58],"importance":[60],"by":[61,109],"considering":[62],"both":[63],"passage":[64],"and":[65,113],"corpus-level":[66],"frequencies,":[67],"leading":[68],"more":[70],"effective":[71],"deletion.":[73],"Experimental":[74],"results":[75],"demonstrate":[76],"approach":[80],"significantly":[81],"improves":[82],"Top-k":[83],"on":[85,97],"smaller":[86],"datasets":[87],"compared":[88],"conventional":[90],"techniques.":[92],"While":[93],"maintaining":[94],"competitive":[95],"performance":[96],"larger-scale":[98],"datasets,":[99],"its":[100,119],"relative":[101],"effectiveness":[102],"particularly":[104],"notable":[105],"scenarios":[107],"characterized":[108],"limited":[110],"training":[111],"severe":[114],"imbalance.":[116],"confirms":[118],"potential":[120],"generalizability":[124],"models.":[128],"The":[129],"source":[130],"code":[131],"publicly":[133],"available":[134],"at":[135],"https://github.com/asmoon002/DPR_TD":[136],".":[137]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
