{"id":"https://openalex.org/W3041690039","doi":"https://doi.org/10.3390/data5030060","title":"An Arabic Dataset for Disease Named Entity Recognition with Multi-Annotation Schemes","display_name":"An Arabic Dataset for Disease Named Entity Recognition with Multi-Annotation Schemes","publication_year":2020,"publication_date":"2020-07-13","ids":{"openalex":"https://openalex.org/W3041690039","doi":"https://doi.org/10.3390/data5030060","mag":"3041690039"},"language":"en","primary_location":{"id":"doi:10.3390/data5030060","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data5030060","pdf_url":"https://www.mdpi.com/2306-5729/5/3/60/pdf","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/5/3/60/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061517602","display_name":"Nasser Alshammari","orcid":"https://orcid.org/0000-0003-4374-3675"},"institutions":[{"id":"https://openalex.org/I199702508","display_name":"Jouf University","ror":"https://ror.org/02zsyt821","country_code":"SA","type":"education","lineage":["https://openalex.org/I199702508"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Nasser Alshammari","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka 72441, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-4374-3675","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka 72441, Saudi Arabia","institution_ids":["https://openalex.org/I199702508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087313412","display_name":"Saad Alanazi","orcid":"https://orcid.org/0000-0002-1714-1948"},"institutions":[{"id":"https://openalex.org/I199702508","display_name":"Jouf University","ror":"https://ror.org/02zsyt821","country_code":"SA","type":"education","lineage":["https://openalex.org/I199702508"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Saad Alanazi","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka 72441, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-1714-1948","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka 72441, Saudi Arabia","institution_ids":["https://openalex.org/I199702508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061517602"],"corresponding_institution_ids":["https://openalex.org/I199702508"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.9512,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81058443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"5","issue":"3","first_page":"60","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9947999715805054,"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/annotation","display_name":"Annotation","score":0.9561137557029724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8262717127799988},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6877245903015137},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6731389760971069},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.580305814743042},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5711981058120728},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5004110336303711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4831477999687195},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46644896268844604},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4452626407146454},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17227232456207275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05796843767166138}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.9561137557029724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262717127799988},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6877245903015137},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6731389760971069},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.580305814743042},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5711981058120728},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5004110336303711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4831477999687195},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46644896268844604},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4452626407146454},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17227232456207275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05796843767166138},{"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/data5030060","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data5030060","pdf_url":"https://www.mdpi.com/2306-5729/5/3/60/pdf","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jdataj:v:5:y:2020:i:3:p:60-:d:383901","is_oa":false,"landing_page_url":"https://www.mdpi.com/2306-5729/5/3/60/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:e3a0d28a58c24e38872ae142f686c631","is_oa":true,"landing_page_url":"https://doaj.org/article/e3a0d28a58c24e38872ae142f686c631","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 5, Iss 3, p 60 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2306-5729/5/3/60/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/data5030060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data; Volume 5; Issue 3; Pages: 60","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/data5030060","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data5030060","pdf_url":"https://www.mdpi.com/2306-5729/5/3/60/pdf","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3041690039.pdf","grobid_xml":"https://content.openalex.org/works/W3041690039.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W89689174","https://openalex.org/W784649594","https://openalex.org/W1153356764","https://openalex.org/W1502473750","https://openalex.org/W1505506221","https://openalex.org/W1580467103","https://openalex.org/W1604667221","https://openalex.org/W1966976587","https://openalex.org/W2033599040","https://openalex.org/W2053154970","https://openalex.org/W2250090865","https://openalex.org/W2250816155","https://openalex.org/W2556849656","https://openalex.org/W3017222382","https://openalex.org/W4294214983","https://openalex.org/W6603699974","https://openalex.org/W6630213884","https://openalex.org/W6691525129"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W1570025324","https://openalex.org/W2116902754","https://openalex.org/W2740145017","https://openalex.org/W4377865234","https://openalex.org/W2166185180"],"abstract_inverted_index":{"This":[0],"article":[1],"outlines":[2],"a":[3,16,82,85],"novel":[4,86],"data":[5],"descriptor":[6],"that":[7,99],"provides":[8],"the":[9,43,50,53,56,68,74,92,102,111,117,120,148,151,160],"Arabic":[10,79,121],"natural":[11],"language":[12],"processing":[13],"community":[14],"with":[15],"dataset":[17,27,90],"dedicated":[18,76],"to":[19,67,77,107],"named":[20,122],"entity":[21,123],"recognition":[22],"tasks":[23],"for":[24,156],"diseases.":[25],"The":[26],"comprises":[28],"more":[29,96],"than":[30],"60":[31],"thousand":[32],"words,":[33],"which":[34],"were":[35],"annotated":[36],"manually":[37],"by":[38,104],"two":[39],"independent":[40],"annotators":[41],"using":[42],"inside\u2013outside":[44],"(IO)":[45],"annotation":[46,54,97,126],"scheme.":[47],"To":[48],"ensure":[49],"reliability":[51],"of":[52,70,88,94,113,119,150],"process,":[55],"inter-annotator":[57],"agreements":[58],"rate":[59],"was":[60],"calculated,":[61],"and":[62,84,109,134,147],"it":[63],"scored":[64],"95.14%.":[65],"Due":[66],"lack":[69],"research":[71],"efforts":[72],"in":[73,159],"literature":[75],"studying":[78],"multi-annotation":[80],"schemes,":[81],"distinguishing":[83],"aspect":[87],"this":[89],"is":[91],"inclusion":[93],"six":[95],"schemes":[98,115,127],"will":[100],"bridge":[101],"gap":[103],"allowing":[105],"researchers":[106],"explore":[108],"compare":[110],"effects":[112],"these":[114],"on":[116],"performance":[118],"recognizers.":[124],"These":[125],"are":[128,154],"IOE,":[129],"IOB,":[130],"BIES,":[131],"IOBES,":[132],"IE,":[133],"BI.":[135],"Additionally,":[136],"five":[137],"linguistic":[138],"features,":[139],"including":[140],"part-of-speech":[141],"tags,":[142],"stopwords,":[143],"gazetteers,":[144],"lexical":[145],"markers,":[146],"presence":[149],"definite":[152],"article,":[153],"provided":[155],"each":[157],"record":[158],"dataset.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-07-16T00:00:00"}
