{"id":"https://openalex.org/W4389374246","doi":"https://doi.org/10.1145/3628797.3628810","title":"Stratified Ranking for Dense Passage Retrieval","display_name":"Stratified Ranking for Dense Passage Retrieval","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389374246","doi":"https://doi.org/10.1145/3628797.3628810"},"language":"en","primary_location":{"id":"doi:10.1145/3628797.3628810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3628810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","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/A5046265942","display_name":"Loi Le Vu","orcid":"https://orcid.org/0009-0008-5881-3983"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Loi Le Vu","raw_affiliation_strings":["CMC Applied Technology Institute, Viet Nam"],"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003530851","display_name":"Dong Nguyen Tien","orcid":"https://orcid.org/0009-0000-3634-257X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Nguyen Tien","raw_affiliation_strings":["CMC Applied Technology Institute, Viet Nam"],"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute, Viet Nam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054771261","display_name":"Tuan Minh Dang","orcid":"https://orcid.org/0000-0002-0913-1598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuan Dang Minh","raw_affiliation_strings":["CMC Applied Technology Institute, Viet Nam"],"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute, Viet Nam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046265942"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16785811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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/ranking","display_name":"Ranking (information retrieval)","score":0.8701330423355103},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.8369924426078796},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.741732656955719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6678285598754883},{"id":"https://openalex.org/keywords/ranking-svm","display_name":"Ranking SVM","score":0.6291459798812866},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6135355234146118},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5091490149497986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47247549891471863},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4406963288784027},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4381967782974243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17929986119270325}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8701330423355103},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8369924426078796},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.741732656955719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6678285598754883},{"id":"https://openalex.org/C124975894","wikidata":"https://www.wikidata.org/wiki/Q7293290","display_name":"Ranking SVM","level":3,"score":0.6291459798812866},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6135355234146118},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5091490149497986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47247549891471863},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4406963288784027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4381967782974243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17929986119270325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3628797.3628810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3628797.3628810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2912924812","https://openalex.org/W2951434086","https://openalex.org/W2970641574","https://openalex.org/W2998702515","https://openalex.org/W3155895380","https://openalex.org/W3157758108","https://openalex.org/W3168875417","https://openalex.org/W3174367567","https://openalex.org/W3185250692","https://openalex.org/W3206455169","https://openalex.org/W4252076394"],"related_works":["https://openalex.org/W3127142483","https://openalex.org/W2138488530","https://openalex.org/W4385565564","https://openalex.org/W2370100764","https://openalex.org/W2031468273","https://openalex.org/W2387658907","https://openalex.org/W2351112195","https://openalex.org/W4378464883","https://openalex.org/W2898073868","https://openalex.org/W2110822809"],"abstract_inverted_index":{"Dense":[0,49],"passage":[1,191],"retrieval":[2,140,192],"has":[3],"recently":[4],"boosted":[5],"the":[6,59,103,122,133,187],"performance":[7],"of":[8,58,102,127,149,178,181,189],"involved":[9,91],"systems":[10],"such":[11],"as":[12],"question":[13],"answering":[14],"or":[15,172],"search":[16],"engine.":[17],"On":[18],"this":[19,40],"problem,":[20],"prior":[21],"works":[22],"trained":[23],"a":[24,44,85,99],"dense":[25,190],"retriever":[26],"by":[27,83,138],"learning":[28,200],"to":[29,120,186,207],"rank,":[30],"i.e.":[31],"ranking":[32,56,180],"relevant/positive":[33],"passages":[34],"higher":[35],"than":[36],"irrelevant/negative":[37],"ones.":[38],"In":[39],"paper,":[41],"we":[42,111],"propose":[43],"Stratified":[45],"Ranking":[46],"approach":[47],"for":[48],"Passage":[50],"Retrieval":[51,155],"(SR-DPR),":[52],"which":[53,71,97],"performs":[54],"three-way":[55],"instead":[57],"typical":[60],"two-way":[61],"positive-negative":[62],"ranking.":[63],"SR-DPR":[64,81,131,157,182],"is":[65,98,118,183],"concerned":[66],"with":[67,92,163],"three":[68,94,113,128],"relevance":[69,95,129],"levels,":[70,96],"are":[72],"positive,":[73],"hard":[74],"negative":[75,87],"and":[76,147],"random/easy":[77],"negative.":[78],"We":[79,202],"train":[80],"model":[82],"minimizing":[84],"contrastive":[86,199],"log-likelihood":[88],"(NLL)":[89],"loss":[90,105],"these":[93],"finer-grained":[100],"version":[101],"N-pair":[104],"[16].":[106],"To":[107],"efficiently":[108],"implement":[109],"SR-DPR,":[110],"designed":[112],"data":[114],"pipelines,":[115],"each":[116],"pipeline":[117],"used":[119],"learn":[121],"contrast":[123],"between":[124],"two":[125],"out":[126],"levels.":[130],"outperforms":[132],"strong":[134],"baseline":[135],"DPR":[136],"[5]":[137],"0.6-1.5%":[139],"accuracy":[141],"on":[142,151],"Natural":[143],"questions":[144],"[6]":[145],"dataset":[146],"3-6%":[148],"that":[150],"Zalo":[152],"Legal":[153],"Text":[154],"dataset.":[156],"also":[158],"gives":[159],"competitive":[160],"results":[161],"compared":[162],"current":[164],"state-of-the-art":[165],"methods":[166],"without":[167],"requiring":[168],"complicated":[169],"training":[170],"regime":[171],"intensive":[173],"hardware":[174],"resources.":[175],"The":[176],"idea":[177],"stratified":[179],"not":[184],"restricted":[185],"scope":[188],"but":[193],"can":[194],"be":[195],"applied":[196],"in":[197],"any":[198],"problem.":[201],"conducted":[203],"detailed":[204],"ablation":[205],"studies":[206],"give":[208],"insights":[209],"into":[210],"SR-DPR\u2019s":[211],"behavior.":[212]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}