{"id":"https://openalex.org/W4406727960","doi":"https://doi.org/10.1109/access.2025.3532767","title":"Toward Automatic Dataset Discovery From Scientific Publications","display_name":"Toward Automatic Dataset Discovery From Scientific Publications","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406727960","doi":"https://doi.org/10.1109/access.2025.3532767"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3532767","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3532767","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3532767","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070433587","display_name":"Sandeep Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sandeep Kumar","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India","Department of Computer science and Engineering, Indian Institute of Technology, Patna, India"],"raw_orcid":"https://orcid.org/0000-0002-0848-632X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Department of Computer science and Engineering, Indian Institute of Technology, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081072666","display_name":"Tirthankar Ghosal","orcid":"https://orcid.org/0000-0002-2358-522X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tirthankar Ghosal","raw_affiliation_strings":["National Center for Computational Sciences, Oak Ridge National Laboratory, Oak Ridge, TN, USA","National Center for Computational Sciences, Oak Ridge National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Computational Sciences, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"National Center for Computational Sciences, Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085370631","display_name":"Asif Ekbal","orcid":"https://orcid.org/0000-0003-3612-8834"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Asif Ekbal","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India","Department of Computer science and Engineering, Indian Institute of Technology, Patna, India"],"raw_orcid":"https://orcid.org/0000-0003-3612-8834","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Department of Computer science and Engineering, Indian Institute of Technology, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070433587"],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00456235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"107961","last_page":"107978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9695000052452087,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9695000052452087,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9465000033378601,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9415000081062317,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6855947375297546},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4198307693004608},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39483609795570374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6855947375297546},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4198307693004608},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39483609795570374}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3532767","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3532767","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8509490d657c4bacaeff65458c39f16e","is_oa":true,"landing_page_url":"https://doaj.org/article/8509490d657c4bacaeff65458c39f16e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 107961-107978 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3532767","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3532767","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4399999976158142,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W75790607","https://openalex.org/W183967578","https://openalex.org/W1490343430","https://openalex.org/W1536826708","https://openalex.org/W1964458660","https://openalex.org/W1981791873","https://openalex.org/W2007343074","https://openalex.org/W2020278455","https://openalex.org/W2087713756","https://openalex.org/W2095655043","https://openalex.org/W2097198341","https://openalex.org/W2113880439","https://openalex.org/W2296283641","https://openalex.org/W2317927196","https://openalex.org/W2479758238","https://openalex.org/W2542020674","https://openalex.org/W2570760970","https://openalex.org/W2613704683","https://openalex.org/W2618665414","https://openalex.org/W2736776866","https://openalex.org/W2769151956","https://openalex.org/W2783207633","https://openalex.org/W2786094103","https://openalex.org/W2808479155","https://openalex.org/W2894170875","https://openalex.org/W2926805670","https://openalex.org/W2949181687","https://openalex.org/W2962903510","https://openalex.org/W2963670884","https://openalex.org/W2963806188","https://openalex.org/W2963964898","https://openalex.org/W2964015378","https://openalex.org/W2964400841","https://openalex.org/W2969723769","https://openalex.org/W2970217403","https://openalex.org/W2970771982","https://openalex.org/W2981089724","https://openalex.org/W2997394673","https://openalex.org/W3008392323","https://openalex.org/W3012892971","https://openalex.org/W3016492791","https://openalex.org/W3017013479","https://openalex.org/W3032553678","https://openalex.org/W3047037404","https://openalex.org/W3104308188","https://openalex.org/W3104748221","https://openalex.org/W3125261728","https://openalex.org/W4231402671","https://openalex.org/W4401857089","https://openalex.org/W4403052255","https://openalex.org/W6600479677","https://openalex.org/W6603544577","https://openalex.org/W6608395927","https://openalex.org/W6631190155","https://openalex.org/W6631918358","https://openalex.org/W6681045971","https://openalex.org/W6682141183","https://openalex.org/W6691660104","https://openalex.org/W6696105951","https://openalex.org/W6712092805","https://openalex.org/W6727690538","https://openalex.org/W6731113888","https://openalex.org/W6752795476","https://openalex.org/W6755207826","https://openalex.org/W6756895183","https://openalex.org/W6768851824","https://openalex.org/W6769722308","https://openalex.org/W6846825190","https://openalex.org/W6847529687","https://openalex.org/W6852893346","https://openalex.org/W6868034431"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Datasets":[0],"are":[1,46,53,85],"a":[2,11,32,96,144,160,170],"crucial":[3,86],"artifact":[4],"in":[5,25,35,66,136,165,196],"research,":[6],"and":[7,22,43,49,71,81,120,129,158,201],"there":[8,29],"is":[9,64],"always":[10],"high":[12],"demand":[13],"for":[14,174],"good":[15,62],"datasets.":[16,39,206],"Due":[17],"to":[18,58,77,87,101,169],"rapid":[19],"scientific":[20,27,89,107],"progress":[21],"exponential":[23],"growth":[24],"the":[26,36,79,88,103,126,155,193,198,203],"literature,":[28],"has":[30],"been":[31],"proportionate":[33],"increase":[34,202],"number":[37],"of":[38,68,83,134,147,163,178,205],"However,":[40],"many":[41],"datasets":[42,63,84],"research":[44,141,157,167],"studies":[45],"left":[47],"unexplored":[48],"under-utilized":[50],"as":[51],"these":[52],"not":[54],"discoverable":[55],"easily,":[56],"leading":[57],"duplicate":[59],"efforts.":[60],"Building":[61],"costly":[65],"terms":[67],"time,":[69],"money,":[70],"human":[72],"effort.":[73],"Hence,":[74],"automated":[75],"tools":[76],"facilitate":[78],"search":[80],"discovery":[82,105],"community.":[90],"In":[91,109],"this":[92,110,185],"work,":[93],"we":[94,112],"investigate":[95],"deep":[97],"neural":[98],"network-based":[99],"architecture":[100],"automate":[102],"dataset":[104,117,138,171,200],"from":[106,140],"publications.":[108,150,181],"paper,":[111],"perform":[113],"two":[114],"tasks":[115],"namely":[116],"mention":[118],"extraction":[119],"entity":[121],"linking.":[122],"Our":[123,151],"method":[124],"outperforms":[125,154],"earlier":[127],"ones":[128],"achieves":[130,159],"an":[131],"F1":[132],"score":[133,162],"56.24":[135],"extracting":[137],"mentions":[139],"papers":[142,168],"on":[143],"popular":[145,176],"corpus":[146,177],"social":[148,179],"science":[149,180],"approach":[152],"also":[153],"prior":[156],"precision":[161],"88.63":[164],"linking":[166],"knowledge":[172],"base":[173],"another":[175],"We":[182],"hope":[183],"that":[184],"system":[186],"will":[187],"further":[188],"promote":[189],"data":[190],"sharing,":[191],"offset":[192],"researchers\u2019":[194],"workload":[195],"identifying":[197],"right":[199],"reusability":[204]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-01-23T00:00:00"}