{"id":"https://openalex.org/W2913964897","doi":"https://doi.org/10.1109/bigdata.2018.8622448","title":"A Machine Learning Based Natural Language Question and Answering System for Healthcare Data Search using Complex Queries","display_name":"A Machine Learning Based Natural Language Question and Answering System for Healthcare Data Search using Complex Queries","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913964897","doi":"https://doi.org/10.1109/bigdata.2018.8622448","mag":"2913964897"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","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/A5109225873","display_name":"Hangu Yeo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hangu Yeo","raw_affiliation_strings":["Department of Next Generation Applications, IBM T. J. Watson Research, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"Department of Next Generation Applications, IBM T. J. Watson Research, Yorktown Heights, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109225873"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3677,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.61209772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2467","last_page":"2474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9979000091552734,"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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/T11719","display_name":"Data Quality and Management","score":0.9884999990463257,"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":0.8760604858398438},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7195308208465576},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7097862958908081},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5885679125785828},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.563332200050354},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5566596388816833},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5362159013748169},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5215082764625549},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4976842701435089},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43103447556495667},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4179608225822449},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33669495582580566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28141123056411743},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23661580681800842},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21106722950935364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8760604858398438},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7195308208465576},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7097862958908081},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5885679125785828},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.563332200050354},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5566596388816833},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5362159013748169},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5215082764625549},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4976842701435089},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43103447556495667},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4179608225822449},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33669495582580566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28141123056411743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23661580681800842},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21106722950935364},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W110935435","https://openalex.org/W1965482737","https://openalex.org/W2066075273","https://openalex.org/W2134489415","https://openalex.org/W2142383816","https://openalex.org/W2187938785","https://openalex.org/W2250510620","https://openalex.org/W2269738476","https://openalex.org/W2403325342","https://openalex.org/W2759659428","https://openalex.org/W6604494194","https://openalex.org/W6687098192","https://openalex.org/W6712896908","https://openalex.org/W6744432207"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2573939812","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W2120098008","https://openalex.org/W4226247999","https://openalex.org/W2898886863","https://openalex.org/W4213176082","https://openalex.org/W1639806124","https://openalex.org/W2187398150"],"abstract_inverted_index":{"Number":[0],"of":[1,17,63,113,169,173,185,202],"use":[2,67],"cases":[3],"in":[4,21,32,218,230,240],"healthcare":[5],"are":[6,19,61,96,120,254],"well":[7],"suited":[8],"as":[9,24,29,45,87,128,177,182,227],"Big":[10,38],"Data":[11,39],"applications.":[12],"In":[13,35],"healthcare,":[14],"large":[15],"volumes":[16],"data":[18,27,31,215,238],"coming":[20,41],"and":[22,54,66,84,123,141,179,232,249,260,272],"stored":[23,217,239],"unstructured":[25],"big":[26],"or":[28],"structured":[30],"relational":[33,242],"database.":[34,220,243],"any":[36],"case,":[37],"is":[40,73,137,268],"to":[42,78,98,146,164,205,246,256,270],"embrace":[43],"SQL":[44],"a":[46,52,74,100,105,171,183],"common":[47],"tool":[48,56],"for":[49,57,70,108],"querying.":[50],"Developing":[51],"question":[53],"answering":[55,124],"the":[58,114,118,150,157,162,165,188,200,209,214,219,237,241,247,250,258,261,266],"users":[59],"that":[60,76],"lack":[62],"specialized":[64],"skillsets":[65],"natural":[68,101],"languages":[69],"complex":[71,125,151,166,192],"queries":[72,103,126,193,229],"challenge":[75],"need":[77],"identify":[79],"significant":[80],"details,":[81],"draw":[82],"inferences":[83],"evaluate":[85],"hypothesis":[86],"how":[88],"domain":[89],"experts":[90,160],"do":[91],"those.":[92],"Although":[93],"NLIDB":[94,144,211,223],"systems":[95,119],"developed":[97],"translate":[99],"language":[102,107],"into":[104,194],"database":[106],"non-technical":[109],"end":[110],"users,":[111],"most":[112],"questions":[115,122],"addressed":[116],"by":[117],"factoid":[121,197],"remains":[127],"an":[129],"open":[130],"research":[131],"problem.":[132],"The":[133,153,221,244],"proposed":[134,189],"auxiliary":[135,154],"system":[136,145,155,190,212,224],"machine":[138],"learning":[139],"based":[140],"extends":[142],"existing":[143,210],"help":[147],"it":[148],"answer":[149,273],"queries.":[152,167,276],"mimics":[156],"way":[158],"human":[159],"reach":[161],"answers":[163,204,245],"Instead":[168],"building":[170],"set":[172],"simple":[174,196],"conditional":[175],"statements":[176],"rules":[178],"invoke":[180],"them":[181],"sequence":[184],"chained":[186],"actions,":[187],"decomposes":[191],"multiple":[195],"sub-queries":[198,226,248],"with":[199,208],"goal":[201],"generating":[203],"each":[206],"sub-query":[207],"from":[213,236,265],"explicitly":[216],"underlying":[222],"takes":[225],"input":[228,275],"parallel":[231],"produces":[233],"query":[234],"results":[235],"desired":[251],"output":[252],"labels":[253],"used":[255,269],"train":[257],"model":[259],"multiclass":[262],"classifier":[263],"produced":[264],"training":[267],"predict":[271],"valid":[274]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}