{"id":"https://openalex.org/W2949475284","doi":null,"title":"Towards Democratizing Data Science with Natural Language Interfaces","display_name":"Towards Democratizing Data Science with Natural Language Interfaces","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2949475284","mag":"2949475284"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt9jm7s302","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9jm7s302","pdf_url":"https://escholarship.org/uc/item/9jm7s302","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/9jm7s302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075435632","display_name":"Yu Su","orcid":"https://orcid.org/0000-0002-6649-4766","observed_orcids":["https://orcid.org/0000-0002-6649-4766","https://orcid.org/0000-0003-4306-0161"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu Su","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4306-0161","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5075435632"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5390999913215637,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.5390999913215637,"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/T10028","display_name":"Topic Modeling","score":0.14180000126361847,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04430000111460686,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/natural-language-interfaces-to-databases","display_name":"natural language interfaces to databases","score":0.8799999952316284},{"id":"https://openalex.org/keywords/natural-language-query-translation","display_name":"natural language query translation","score":0.5230000019073486},{"id":"https://openalex.org/keywords/crowdsourced-data-collection","display_name":"crowdsourced data collection","score":0.7540000081062317},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.7049999833106995},{"id":"https://openalex.org/keywords/data-science-platform","display_name":"data science platform","score":0.5249999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492493987083435},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5208821296691895},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47997379302978516},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.44366705417633057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2992701828479767},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18585339188575745}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:escholarship.org/ark:/13030/qt9jm7s302","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9jm7s302","pdf_url":"https://escholarship.org/uc/item/9jm7s302","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},{"id":"pmh:qt9jm7s302","doi":null,"is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/9jm7s302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Su, Yu. (2018). Towards Democratizing Data Science with Natural Language Interfaces. 0035: Computer Science. Retrieved from: http://www.escholarship.org/uc/item/9jm7s302","raw_type":"dissertation"},{"id":"mag:2949475284","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/content/qt9jm7s302/qt9jm7s302.pdf?t=prjzzu","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt9jm7s302","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9jm7s302","pdf_url":"https://escholarship.org/uc/item/9jm7s302","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3481815549","display_name":"CAREER: Graph Information System: Deciphering Complex Networks","funder_award_id":"0954125","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6383328962","display_name":"III: Small: Knowledge Graph Query Processing and Benchmarking","funder_award_id":"1528175","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949475284.pdf","grobid_xml":"https://content.openalex.org/works/W2949475284.grobid-xml"},"referenced_works_count":97,"referenced_works":["https://openalex.org/W22861983","https://openalex.org/W580074167","https://openalex.org/W1496189301","https://openalex.org/W1539162551","https://openalex.org/W1552847225","https://openalex.org/W1577231857","https://openalex.org/W1615991656","https://openalex.org/W1646084575","https://openalex.org/W1904365287","https://openalex.org/W1948566616","https://openalex.org/W1992712260","https://openalex.org/W2011992920","https://openalex.org/W2014703436","https://openalex.org/W2024888189","https://openalex.org/W2028175314","https://openalex.org/W2036001619","https://openalex.org/W2090243146","https://openalex.org/W2094728533","https://openalex.org/W2096873754","https://openalex.org/W2103305545","https://openalex.org/W2107618763","https://openalex.org/W2118781169","https://openalex.org/W2120354757","https://openalex.org/W2120708938","https://openalex.org/W2123770198","https://openalex.org/W2126170172","https://openalex.org/W2130942839","https://openalex.org/W2131726681","https://openalex.org/W2134557242","https://openalex.org/W2138857742","https://openalex.org/W2141739114","https://openalex.org/W2147953360","https://openalex.org/W2148721079","https://openalex.org/W2152112919","https://openalex.org/W2153579005","https://openalex.org/W2154268919","https://openalex.org/W2157331557","https://openalex.org/W2158108973","https://openalex.org/W2158396456","https://openalex.org/W2163274265","https://openalex.org/W2163561827","https://openalex.org/W2165698076","https://openalex.org/W2167665328","https://openalex.org/W2170738476","https://openalex.org/W2172268343","https://openalex.org/W2174945390","https://openalex.org/W2189089430","https://openalex.org/W2236233024","https://openalex.org/W2250225488","https://openalex.org/W2250533497","https://openalex.org/W2250539671","https://openalex.org/W2250889812","https://openalex.org/W2251044566","https://openalex.org/W2251079237","https://openalex.org/W2251089933","https://openalex.org/W2251287417","https://openalex.org/W2251672533","https://openalex.org/W2251957808","https://openalex.org/W2252136820","https://openalex.org/W2269738476","https://openalex.org/W2271840356","https://openalex.org/W2295690548","https://openalex.org/W2302963717","https://openalex.org/W2304545146","https://openalex.org/W2331728731","https://openalex.org/W2342096063","https://openalex.org/W2410540304","https://openalex.org/W2416885651","https://openalex.org/W2467589492","https://openalex.org/W2511108736","https://openalex.org/W2511149293","https://openalex.org/W2546950329","https://openalex.org/W2561148973","https://openalex.org/W2566402689","https://openalex.org/W2586850891","https://openalex.org/W2587586352","https://openalex.org/W2605214337","https://openalex.org/W2611818442","https://openalex.org/W2745934983","https://openalex.org/W2751448157","https://openalex.org/W2758826377","https://openalex.org/W2767057583","https://openalex.org/W2796544889","https://openalex.org/W2798753108","https://openalex.org/W2899363852","https://openalex.org/W2950109442","https://openalex.org/W2950444459","https://openalex.org/W2962728167","https://openalex.org/W2963069010","https://openalex.org/W2963143606","https://openalex.org/W2963655793","https://openalex.org/W2963794306","https://openalex.org/W2963847417","https://openalex.org/W2963899988","https://openalex.org/W2963941871","https://openalex.org/W2964121744","https://openalex.org/W2964212344"],"related_works":["https://openalex.org/W4321485206","https://openalex.org/W7049008116","https://openalex.org/W7113604812","https://openalex.org/W4285249723","https://openalex.org/W4293160456","https://openalex.org/W3132293665","https://openalex.org/W2995612754","https://openalex.org/W4206029745","https://openalex.org/W7083584081","https://openalex.org/W7037190006"],"abstract_inverted_index":{"Data":[0],"science":[1,24,56,332],"has":[2],"the":[3,10,51,58,87,107,126,139,149,213,217,225,252,300,327],"potential":[4,14],"to":[5,18,50,75,105,124,145,196,286,338],"reshape":[6],"many":[7],"sectors":[8],"of":[9,28,34,54,68,89,138,209,216,228,236,256,364],"modern":[11],"society.":[12],"This":[13],"can":[15,173,294,336,354],"be":[16],"realized":[17],"its":[19],"maximum":[20],"only":[21],"when":[22],"data":[23,36,40,55,69,83,90,127,147,181,210,262,273,306,331,344],"becomes":[25],"democratized,":[26],"instead":[27,363],"centralized":[29],"in":[30,47,92,179,322],"a":[31,77,82,98,176,184,198,203,240,264,283,304],"small":[32],"group":[33],"expert":[35],"scientists.":[37],"However,":[38,183],"with":[39,288],"becoming":[41],"more":[42],"massive":[43],"and":[44,64,111,113,135,212,280,310,320,341,360,369],"heterogeneous,":[45],"standing":[46],"stark":[48],"contrast":[49],"spreading":[52],"demand":[53],"is":[57,148,188,239],"growing":[59],"gap":[60,108],"between":[61,109],"human":[62,376],"users":[63,110,118,144,166,290,353],"data:":[65],"Every":[66],"type":[67],"requires":[70],"extensive":[71,346],"specialized":[72,347],"training,":[73],"either":[74],"learn":[76],"specific":[78],"query":[79],"language":[80,103,163,171,200,230,246,313],"or":[81],"analytics":[84,128],"software.":[85],"Towards":[86],"democratization":[88],"science,":[91],"this":[93,237,323],"dissertation":[94,238,324],"we":[95],"systematically":[96],"investigate":[97],"promising":[99],"research":[100],"direction,":[101],"natural":[102,162,170,199,229,245,312],"interface,":[104],"bridge":[106],"data,":[112],"make":[114],"it":[115,293],"easier":[116],"for":[117,131,142,202,243,248,308,315,329],"who":[119],"are":[120,222],"less":[121],"technically":[122],"proficient":[123],"access":[125,146],"power":[129],"needed":[130],"on-demand":[132],"problem":[133],"solving":[134],"decision":[136,361],"making.One":[137],"largest":[140],"obstacles":[141],"general":[143],"proficiency":[150],"requirement":[151],"on":[152,357],"formal":[153,168],"languages":[154],"(e.g.,":[155],"SQL)":[156],"that":[157,187,292,334],"machines":[158,374],"use.":[159],"Automatically":[160],"parsing":[161],"commands":[164],"from":[165,274],"into":[167],"languages,":[169],"interfaces":[172,247,314],"thus":[174],"play":[175],"critical":[177],"role":[178],"democratizing":[180],"science.":[182],"pressing":[185],"question":[186],"largely":[189],"left":[190],"unanswered":[191],"so":[192,291],"far":[193],"is,":[194],"how":[195],"bootstrap":[197],"interface":[201],"new":[204,249],"domain?":[205],"The":[206,232],"high":[207],"cost":[208,266],"collection":[211],"data-hungry":[214],"nature":[215],"mainstream":[218],"neural":[219],"network":[220],"models":[221],"significantly":[223],"limiting":[224],"wide":[226],"application":[227],"interfaces.":[231],"main":[233],"technical":[234],"contribution":[235],"systematic":[241],"framework":[242,254],"bootstrapping":[244,309],"domains.":[250],"Specifically,":[251],"proposed":[253],"consists":[255],"three":[257,301],"complimentary":[258],"methods:":[259],"(1)":[260],"Collecting":[261],"at":[263],"low":[265],"via":[267,277],"crowdsourcing,":[268],"(2)":[269],"leveraging":[270],"existing":[271],"NLI":[272],"other":[275],"domains":[276],"transfer":[278],"learning,":[279],"(3)":[281],"letting":[282],"bootstrapped":[284],"model":[285],"interact":[287],"real":[289],"refine":[295],"itself":[296],"over":[297],"time.":[298],"Combining":[299],"methods":[302],"forms":[303],"closed":[305],"loop":[307],"refining":[311],"any":[316],"domain.The":[317],"developed":[318],"methodologies":[319],"frameworks":[321],"hence":[325],"pave":[326],"path":[328],"building":[330],"platforms":[333],"everyone":[335],"use":[337],"process,":[339],"query,":[340],"analyze":[342],"their":[343],"without":[345],"training.":[348],"With":[349],"such":[350],"AI-powered":[351],"platforms,":[352],"stay":[355],"focused":[356],"high-level":[358],"thinking":[359],"making,":[362],"overwhelmed":[365],"by":[366],"low-level":[367],"implementation":[368],"programming":[370],"details":[371],"---":[372],"``\\\\emph{Let":[373],"understand":[375],"thinking.":[377],"Don't":[378],"let":[379],"humans":[380],"think":[381],"like":[382],"machines}.''":[383]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-06-27T00:00:00"}