{"id":"https://openalex.org/W4306317384","doi":"https://doi.org/10.1145/3511808.3557675","title":"PubMed Author-assigned Keyword Extraction (PubMedAKE) Benchmark","display_name":"PubMed Author-assigned Keyword Extraction (PubMedAKE) Benchmark","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317384","doi":"https://doi.org/10.1145/3511808.3557675","pmid":"https://pubmed.ncbi.nlm.nih.gov/36382341"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557675","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9652778","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082344647","display_name":"Jiasheng Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiasheng Sheng","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073022416","display_name":"Zelalem Gero","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zelalem Gero","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022272635","display_name":"Joyce C. Ho","orcid":"https://orcid.org/0000-0001-9168-3916"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joyce C. Ho","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6742,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70456523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2022","issue":null,"first_page":"4470","last_page":"4474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T13083","display_name":"Advanced Text Analysis Techniques","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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8957921862602234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8335866928100586},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.7404746413230896},{"id":"https://openalex.org/keywords/keyword-search","display_name":"Keyword search","score":0.6663818955421448},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5521069765090942},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5239834189414978},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4220063090324402},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.419875830411911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3259107768535614}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8957921862602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335866928100586},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.7404746413230896},{"id":"https://openalex.org/C2988412617","wikidata":"https://www.wikidata.org/wiki/Q7441656","display_name":"Keyword search","level":2,"score":0.6663818955421448},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5521069765090942},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5239834189414978},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4220063090324402},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.419875830411911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3259107768535614},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3511808.3557675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557675","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmid:36382341","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36382341","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... ACM International Conference on Information & Knowledge Management. ACM International Conference on Information and Knowledge Management","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9652778","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9652778","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc ACM Int Conf Inf Knowl Manag","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:9652778","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9652778","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc ACM Int Conf Inf Knowl Manag","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2125284036","display_name":null,"funder_award_id":"R01 LM013323","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G2886520211","display_name":"SCH: INT Re-envisioned Chat-assessment for Real-time Investigating of Nursing and Guidance ","funder_award_id":"5r01lm013323-03","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2893488462","display_name":"BigData:IA:Collaborative Research: TIMES: A tensor factorization platform for spatio-temporal data","funder_award_id":"1838200","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3813450588","display_name":"Leveraging modern analytic approaches to improve diabetes outcomes","funder_award_id":"5k01lm012924-03","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4309864222","display_name":null,"funder_award_id":"K01 LM012924","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G7117717954","display_name":"SCH: INT Re-envisioned Chat-assessment for Real-time Investigating of Nursing and Guidance ","funder_award_id":"5r01lm013323-04","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W378747138","https://openalex.org/W1603598191","https://openalex.org/W1983873791","https://openalex.org/W1991570251","https://openalex.org/W2025809917","https://openalex.org/W2064418625","https://openalex.org/W2129557600","https://openalex.org/W2143017621","https://openalex.org/W2153366821","https://openalex.org/W2156626957","https://openalex.org/W2157331557","https://openalex.org/W2214674395","https://openalex.org/W2251476947","https://openalex.org/W2522871920","https://openalex.org/W2740811004","https://openalex.org/W2771976988","https://openalex.org/W2792059528","https://openalex.org/W2807498782","https://openalex.org/W2888766462","https://openalex.org/W2890484448","https://openalex.org/W2911489562","https://openalex.org/W2914076857","https://openalex.org/W2949963192","https://openalex.org/W2955273711","https://openalex.org/W2963245897","https://openalex.org/W2963265326","https://openalex.org/W2973226110","https://openalex.org/W3004877964","https://openalex.org/W3015316465","https://openalex.org/W3015784350","https://openalex.org/W3033577848","https://openalex.org/W3046517428","https://openalex.org/W3105854766","https://openalex.org/W3140514123","https://openalex.org/W3172208128","https://openalex.org/W3184133963","https://openalex.org/W3191611757","https://openalex.org/W4385574038","https://openalex.org/W6612948155"],"related_works":["https://openalex.org/W2537849043","https://openalex.org/W2314592662","https://openalex.org/W2606928473","https://openalex.org/W4306317384","https://openalex.org/W2972097726","https://openalex.org/W190266872","https://openalex.org/W2785037737","https://openalex.org/W2084225939","https://openalex.org/W3093477062","https://openalex.org/W3045530941"],"abstract_inverted_index":{"With":[0],"the":[1,8,30,36,51,61,74,93],"ever-increasing":[2],"abundance":[3],"of":[4,10,32,38,56],"biomedical":[5,24,102],"articles,":[6],"improving":[7],"accuracy":[9],"keyword":[11,21,46,76,98],"search":[12],"results":[13,87],"becomes":[14],"crucial":[15],"for":[16,23,95,101],"ensuring":[17],"reproducible":[18],"research.":[19],"However,":[20],"extraction":[22,47,77,99],"articles":[25,59],"is":[26,43,73],"hard":[27],"due":[28],"to":[29,82],"existence":[31],"obscure":[33],"keywords":[34,55],"and":[35,54],"lack":[37],"a":[39],"comprehensive":[40],"benchmark.":[41],"PubMedAKE":[42],"an":[44],"author-assigned":[45],"dataset":[48],"that":[49],"contains":[50],"title,":[52],"abstract,":[53],"over":[57],"843,269":[58],"from":[60],"PubMed":[62],"open":[63],"access":[64],"subset":[65],"database.":[66],"This":[67],"dataset,":[68],"publicly":[69],"available":[70],"on":[71],"Zenodo,":[72],"largest":[75],"benchmark":[78],"with":[79],"sufficient":[80],"samples":[81],"train":[83],"neural":[84],"networks.":[85],"Experimental":[86],"using":[88],"state-of-the-art":[89],"baseline":[90],"methods":[91,100],"illustrate":[92],"need":[94],"developing":[96],"automatic":[97],"literature.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}