{"id":"https://openalex.org/W4405247832","doi":"https://doi.org/10.1145/3707449","title":"Self Data Augmentation for Open Domain Question Answering","display_name":"Self Data Augmentation for Open Domain Question Answering","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4405247832","doi":"https://doi.org/10.1145/3707449"},"language":"en","primary_location":{"id":"doi:10.1145/3707449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3707449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3707449","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3707449","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053100078","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0002-1449-5046"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065044467","display_name":"Mengqi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Zheng","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","College of Computer Science and Software Engineering, Shenzhen University","College of Computer Science and Software Engineering, Shenzhen University; Visual Perception and Intelligent Analysis Engineering Center, Quanzhou Vocational College of Economics and Business, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University; Visual Perception and Intelligent Analysis Engineering Center, Quanzhou Vocational College of Economics and Business, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008919268","display_name":"Shangsi Chen","orcid":"https://orcid.org/0000-0003-3445-2075"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangsi Chen","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349055","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-7731-8258"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","College of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400486","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0001-6745-286X"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["University of Liverpool, Liverpool, United Kingdom of Great Britain and Northern Ireland","University of Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Liverpool, Liverpool, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"University of Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053100078"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":1.6845,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.872743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"43","issue":"2","first_page":"1","last_page":"35"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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":0.8304385542869568},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7678158283233643},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6534807085990906},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6498820185661316},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5726868510246277},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5276476144790649},{"id":"https://openalex.org/keywords/open-domain","display_name":"Open domain","score":0.5105639696121216},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4806565046310425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4739389717578888},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4686310291290283},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4564954340457916},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.42617443203926086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304385542869568},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7678158283233643},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6534807085990906},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6498820185661316},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5726868510246277},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5276476144790649},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.5105639696121216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4806565046310425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4739389717578888},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4686310291290283},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4564954340457916},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.42617443203926086},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3707449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3707449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3707449","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3707449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3707449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3707449","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2563776749","display_name":null,"funder_award_id":"202205","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3472539505","display_name":null,"funder_award_id":"202205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4488680036","display_name":null,"funder_award_id":"2022A15","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6106196308","display_name":null,"funder_award_id":"51501012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6275353366","display_name":null,"funder_award_id":"2022A1515010129","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G655638088","display_name":null,"funder_award_id":"62106147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7040646940","display_name":null,"funder_award_id":"62206179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405247832.pdf","grobid_xml":"https://content.openalex.org/works/W4405247832.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W2252136820","https://openalex.org/W2557764419","https://openalex.org/W2606964149","https://openalex.org/W2740321901","https://openalex.org/W2912924812","https://openalex.org/W2913077324","https://openalex.org/W2951434086","https://openalex.org/W2962985038","https://openalex.org/W2963339397","https://openalex.org/W2963609889","https://openalex.org/W2964823609","https://openalex.org/W2973947483","https://openalex.org/W2981852735","https://openalex.org/W2988421999","https://openalex.org/W3021397474","https://openalex.org/W3035169992","https://openalex.org/W3093655911","https://openalex.org/W3099700870","https://openalex.org/W3102378333","https://openalex.org/W3156789018","https://openalex.org/W3168875417","https://openalex.org/W3174367567","https://openalex.org/W3177415603","https://openalex.org/W3199493219","https://openalex.org/W3201053014","https://openalex.org/W4205480697","https://openalex.org/W4206104244","https://openalex.org/W4206121183","https://openalex.org/W4206633947","https://openalex.org/W4213088336","https://openalex.org/W4252076394","https://openalex.org/W4281477951","https://openalex.org/W4283750777","https://openalex.org/W4284669679","https://openalex.org/W4285185528","https://openalex.org/W4285214521","https://openalex.org/W4285231210","https://openalex.org/W4285236375","https://openalex.org/W4288089799","https://openalex.org/W4319918988","https://openalex.org/W4379388346","https://openalex.org/W4382239620","https://openalex.org/W4382449327","https://openalex.org/W4385571153","https://openalex.org/W4385572334","https://openalex.org/W4385572856","https://openalex.org/W4385573057","https://openalex.org/W4386566764","https://openalex.org/W4387259549","https://openalex.org/W4392903827","https://openalex.org/W4393160365","https://openalex.org/W4399258424","https://openalex.org/W4402669975","https://openalex.org/W4404781249","https://openalex.org/W4404792889"],"related_works":["https://openalex.org/W2391533720","https://openalex.org/W2951097643","https://openalex.org/W4309395021","https://openalex.org/W3091989500","https://openalex.org/W3215363805","https://openalex.org/W204133468","https://openalex.org/W2991310128","https://openalex.org/W4307481286","https://openalex.org/W2395174199","https://openalex.org/W2123359227"],"abstract_inverted_index":{"Information":[0],"Retrieval":[1],"(IR)":[2],"constitutes":[3],"a":[4,63,110,147,219,262],"vital":[5],"facet":[6],"of":[7,18,24,58,70,96,107,124,134,237],"Open":[8],"Domain":[9],"Question":[10],"Answering":[11],"(ODQA)":[12],"systems,":[13],"focusing":[14],"on":[15,37,121,210,266],"the":[16,68,94,102,168,195,199,230,235,267],"exploration":[17],"pertinent":[19],"information":[20],"within":[21],"extensive":[22,212],"collections":[23],"passages,":[25],"such":[26,128],"as":[27,109,129],"Wikipedia,":[28],"to":[29,67,89,160,187,202,254],"facilitate":[30],"subsequent":[31],"reader":[32],"processing.":[33],"Historically,":[34],"IR":[35],"relied":[36],"textual":[38],"overlaps":[39],"for":[40,112,175],"relevant":[41,172],"context":[42,91],"retrieval,":[43],"employing":[44],"methods":[45,117,186],"like":[46],"BM25":[47],"and":[48,140,216],"TF-IDF,":[49],"which,":[50],"however,":[51],"lacked":[52],"natural":[53,97],"language":[54,98],"understanding.":[55],"The":[56,132],"advent":[57],"deep":[59],"learning":[60],"ushered":[61],"in":[62],"new":[64],"era,":[65],"leading":[66],"introduction":[69],"Dense":[71],"Passage":[72],"Retrievers":[73],"(DPR),":[74],"shows":[75],"superiority":[76],"over":[77],"traditional":[78],"sparse":[79],"retrievers.":[80,257],"These":[81],"dense":[82,256],"retrievers":[83],"leverage":[84],"Pre-Trained":[85],"Language":[86],"Models":[87],"(PLMs)":[88],"initialize":[90],"encoders,":[92],"enabling":[93],"extraction":[95],"representations.":[99],"They":[100],"utilize":[101],"distance":[103],"between":[104],"latent":[105],"vectors":[106],"contexts":[108],"metric":[111],"assessing":[113],"similarity.":[114],"However,":[115],"DPR":[116,158],"are":[118],"heavily":[119],"reliant":[120],"large":[122],"volumes":[123],"meticulously":[125],"labeled":[126],"data,":[127,269],"Natural":[130],"Questions.":[131],"process":[133,169],"data":[135,149,244],"labeling":[136],"is":[137,251],"both":[138],"costly":[139],"time-intensive.":[141],"In":[142],"this":[143],"article,":[144],"we":[145,166,193,259],"propose":[146],"novel":[148],"augmentation":[150,245],"methodology":[151],"Self":[152],"Data":[153],"Augmentation":[154],"(SDA)":[155],"that":[156],"employs":[157],"models":[159],"automatically":[161],"annotate":[162,188],"unanswered":[163,200],"questions.":[164,178],"Specifically,":[165],"initiate":[167],"by":[170],"retrieving":[171],"pseudo":[173,190],"passages":[174,197],"these":[176,189],"unlabeled":[177],"We":[179],"subsequently":[180],"introduce":[181],"three":[182,225],"distinct":[183],"passage":[184],"selection":[185],"passages.":[191],"Ultimately,":[192],"amalgamate":[194],"pseudo-labeled":[196],"with":[198],"questions":[201],"create":[203],"augmented":[204,239,268],"data.":[205,240],"Our":[206],"experimental":[207],"evaluations":[208],"conducted":[209,261],"two":[211],"datasets":[213],"(Natural":[214],"Questions":[215],"TriviaQA),":[217],"alongside":[218],"relatively":[220],"small":[221],"dataset":[222],"(WebQuestions),":[223],"utilizing":[224],"diverse":[226],"base":[227],"models,":[228],"illustrate":[229],"significant":[231],"enhancement":[232],"achieved":[233],"through":[234],"incorporation":[236],"freshly":[238],"Moreover,":[241],"our":[242,273],"proposed":[243],"method":[246],"exhibits":[247],"remarkable":[248],"flexibility,":[249],"which":[250,270],"readily":[252],"adaptable":[253],"various":[255],"Additionally,":[258],"have":[260],"comprehensive":[263],"human":[264],"study":[265],"further":[271],"supports":[272],"conclusions.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}