{"id":"https://openalex.org/W3134017289","doi":null,"title":"Deep Learning for Unstructured Data by Leveraging Domain Knowledge","display_name":"Deep Learning for Unstructured Data by Leveraging Domain Knowledge","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W3134017289","mag":"3134017289"},"language":"en","primary_location":{"id":"pmh:oai:scholarshare.temple.edu:20.500.12613/3931","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12613/3931","pdf_url":"http://hdl.handle.net/20.500.12613/3931","source":{"id":"https://openalex.org/S4306402624","display_name":"TUScholarShare (Temple University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I84392919","host_organization_name":"Temple University","host_organization_lineage":["https://openalex.org/I84392919"],"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":"Thesis/Dissertation"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.12613/3931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046910090","display_name":"Shanshan Zhang","orcid":"https://orcid.org/0000-0002-6802-8769","observed_orcids":["https://orcid.org/0000-0002-6802-8769","https://orcid.org/0000-0003-3720-8078"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shanshan Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6802-8769","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5046910090"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10028","display_name":"Topic Modeling","score":0.8676999807357788,"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":0.8676999807357788,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.08739999681711197,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.01860000006854534,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/unstructured-data","display_name":"unstructured data","score":0.9670000076293945},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.6809999942779541},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"domain knowledge","score":0.7770000100135803},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.6359999775886536},{"id":"https://openalex.org/keywords/noisy-text","display_name":"noisy text","score":0.7889999747276306},{"id":"https://openalex.org/keywords/tweets","display_name":"tweets","score":0.6510000228881836},{"id":"https://openalex.org/keywords/disaster-tweets","display_name":"disaster tweets","score":0.5329999923706055},{"id":"https://openalex.org/keywords/word-clustering","display_name":"word clustering","score":0.8629999756813049},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"human-in-the-loop","score":0.6769999861717224},{"id":"https://openalex.org/keywords/entity-identification","display_name":"entity identification","score":0.8799999952316284},{"id":"https://openalex.org/keywords/regular-expressions","display_name":"regular expressions","score":0.7540000081062317},{"id":"https://openalex.org/keywords/entity-recognition","display_name":"entity recognition","score":0.6309999823570251},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.5479999780654907},{"id":"https://openalex.org/keywords/graph-classification","display_name":"graph classification","score":0.39100000262260437},{"id":"https://openalex.org/keywords/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.44600000977516174},{"id":"https://openalex.org/keywords/graph-attention-networks","display_name":"graph attention networks","score":0.48500001430511475},{"id":"https://openalex.org/keywords/graph-autoencoder","display_name":"graph autoencoder","score":0.4620000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6286075711250305},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5099881887435913},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.470415860414505},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.424194872379303},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41323062777519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37457913160324097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:scholarshare.temple.edu:20.500.12613/3931","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12613/3931","pdf_url":"http://hdl.handle.net/20.500.12613/3931","source":{"id":"https://openalex.org/S4306402624","display_name":"TUScholarShare (Temple University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I84392919","host_organization_name":"Temple University","host_organization_lineage":["https://openalex.org/I84392919"],"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":"Thesis/Dissertation"},{"id":"mag:3134017289","doi":null,"is_oa":false,"landing_page_url":"https://scholarshare.temple.edu/handle/20.500.12613/3931","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:scholarshare.temple.edu:20.500.12613/3931","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12613/3931","pdf_url":"http://hdl.handle.net/20.500.12613/3931","source":{"id":"https://openalex.org/S4306402624","display_name":"TUScholarShare (Temple University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I84392919","host_organization_name":"Temple University","host_organization_lineage":["https://openalex.org/I84392919"],"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":"Thesis/Dissertation"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2653471122","display_name":"BIGDATA: Collaborative Research: F: Streaming Architecture for Continuous Entity Linking in Social Media","funder_award_id":"1546480","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4989717163","display_name":"BDD: Dynamic Evolution of Smart-Phone Based Emergency Communications Network","funder_award_id":"1461932","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/F4320312387","display_name":"Temple University","ror":"https://ror.org/00kx1jb78"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134017289.pdf","grobid_xml":"https://content.openalex.org/works/W3134017289.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W72959484","https://openalex.org/W641710284","https://openalex.org/W1505680913","https://openalex.org/W1508480967","https://openalex.org/W1602694398","https://openalex.org/W1832693441","https://openalex.org/W1854884267","https://openalex.org/W1934362406","https://openalex.org/W1940872118","https://openalex.org/W1956471287","https://openalex.org/W1964189668","https://openalex.org/W1978633512","https://openalex.org/W1987538593","https://openalex.org/W2026213144","https://openalex.org/W2033206800","https://openalex.org/W2038941723","https://openalex.org/W2039532210","https://openalex.org/W2045865594","https://openalex.org/W2059383863","https://openalex.org/W2080100102","https://openalex.org/W2080666934","https://openalex.org/W2097998348","https://openalex.org/W2101609803","https://openalex.org/W2106950427","https://openalex.org/W2112184938","https://openalex.org/W2113459411","https://openalex.org/W2121227244","https://openalex.org/W2131744502","https://openalex.org/W2134150392","https://openalex.org/W2138857742","https://openalex.org/W2142377809","https://openalex.org/W2142498761","https://openalex.org/W2148540243","https://openalex.org/W2153693853","https://openalex.org/W2157765050","https://openalex.org/W2159156271","https://openalex.org/W2170682101","https://openalex.org/W2179519966","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2251939518","https://openalex.org/W2252027530","https://openalex.org/W2275294428","https://openalex.org/W2280776734","https://openalex.org/W2295625793","https://openalex.org/W2296283641","https://openalex.org/W2313966941","https://openalex.org/W2339673956","https://openalex.org/W2339995566","https://openalex.org/W2352719088","https://openalex.org/W2460513959","https://openalex.org/W2464725281","https://openalex.org/W2493916176","https://openalex.org/W2509361447","https://openalex.org/W2510940142","https://openalex.org/W2529184846","https://openalex.org/W2535764243","https://openalex.org/W2579353374","https://openalex.org/W2597655663","https://openalex.org/W2602288119","https://openalex.org/W2604184171","https://openalex.org/W2606780347","https://openalex.org/W2609602893","https://openalex.org/W2737092125","https://openalex.org/W2740582239","https://openalex.org/W2770860644","https://openalex.org/W2785787385","https://openalex.org/W2787560479","https://openalex.org/W2799269579","https://openalex.org/W2835793135","https://openalex.org/W2891383691","https://openalex.org/W2891680269","https://openalex.org/W2896457183","https://openalex.org/W2903158431","https://openalex.org/W2933966394","https://openalex.org/W2949240516","https://openalex.org/W2949548130","https://openalex.org/W2950742292","https://openalex.org/W2962779279","https://openalex.org/W2962902328","https://openalex.org/W2963341956","https://openalex.org/W2963687836","https://openalex.org/W2963711743","https://openalex.org/W2964250510","https://openalex.org/W2964343412","https://openalex.org/W4394657320"],"related_works":["https://openalex.org/W3194667523","https://openalex.org/W2940490924","https://openalex.org/W2980967089","https://openalex.org/W2952580099","https://openalex.org/W7125529448","https://openalex.org/W2973900266","https://openalex.org/W6999710647","https://openalex.org/W3042071233","https://openalex.org/W4409212019","https://openalex.org/W132411187"],"abstract_inverted_index":{"Unstructured":[0],"data":[1,46,57,237,387],"such":[2,91,102,194,214],"as":[3,92,195,215,318,541],"texts,":[4],"strings,":[5],"images,":[6],"audios,":[7],"videos":[8],"are":[9,148,155,220,252,539,600],"everywhere":[10],"due":[11],"to":[12,53,78,120,150,208,238,300,304,342,372,383,430,454,506,585],"the":[13,17,20,55,182,263,295,315,328,337,343,348,374,408,425,437,469,496,523,610,633],"social":[14],"interaction":[15],"on":[16,163,347,401,616],"Internet":[18],"and":[19,27,84,95,108,124,171,210,267,276,313,459,477,486,528,534,556,577],"high-throughput":[21],"technology":[22],"in":[23,48,112,190,273,468,490,522],"sciences,":[24,530],"e.g.,":[25],"chemistry":[26],"biology.":[28],"However,":[29,204,609],"for":[30,127,169,186,290,320,361,393,561,575,605],"traditional":[31],"machine":[32,68,196],"learning":[33,69,114,138,167,177,227,231,271,382,546,552],"algorithms,":[34],"classifying":[35,44],"a":[36,45,49,73,79,88,117,140,285,308,357,389,418,450,465,571],"text":[37,170,212,470],"document":[38],"is":[39,75,105,333,340,452,549,559,583,596],"far":[40],"more":[41],"difficult":[42],"than":[43,602],"entry":[47],"spreadsheet.":[50],"We":[51,282,298,354,422,441,494,569,592,620],"have":[52,178,517],"convert":[54],"unstructured":[56,128],"into":[58,87,307,388],"some":[59],"numeric":[60],"vectors":[61,104],"which":[62,154],"can":[63,612],"then":[64,85,355],"be":[65,614],"understood":[66],"by":[67,481],"algorithms.":[70],"For":[71,130],"example,":[72,131],"sentence":[74],"first":[76,283],"converted":[77],"vector":[80,97],"of":[81,101,142,157,235,311,330,377,380,427,475,500,525,537,551,564],"word":[82,143,316,483],"counts,":[83],"fed":[86],"classification":[89,345],"algorithm":[90],"logistic":[93],"regression":[94],"support":[96],"machine.":[98],"The":[99,399],"creation":[100],"numerical":[103],"very":[106,412],"challenging":[107],"difficult.":[109],"Recent":[110],"progress":[111],"deep":[113,166,176,226,230,270,286,381,545,635],"provides":[115],"us":[116],"new":[118,269,390],"way":[119],"jointly":[121],"learn":[122,151,384,587],"features":[123,319],"train":[125,239],"classifiers":[126],"data.":[129,173,398],"recurrent":[132],"neural":[133,146,244,515,579,628,636],"networks":[134,147,516,599,629],"proved":[135],"successful":[136],"at":[137],"from":[139,152,364,385,396,553,590],"sequence":[141],"indices;":[144],"convolutional":[145],"effective":[149,241],"videos,":[153],"sequences":[156],"pixel":[158],"matrices.":[159],"Our":[160,323,368],"research":[161],"focuses":[162],"developing":[164],"novel":[165],"approaches":[168,272],"graph":[172,554,557,573,598],"Breakthroughs":[174],"using":[175],"been":[179,518],"made":[180],"during":[181,294],"last":[183],"few":[184],"years":[185],"many":[187],"core":[188],"tasks":[189,278],"natural":[191,250],"language":[192,251],"processing,":[193],"translation,":[197],"POS":[198],"tagging,":[199],"named":[200],"entity":[201,362,394,403,428,438],"recognition,":[202],"etc.":[203],"when":[205,327,449,503],"it":[206,505,595],"comes":[207],"informal":[209,256],"noisy":[211,280,365,511],"data,":[213],"tweets,":[216],"HTMLs,":[217],"OCR,":[218],"there":[219],"two":[221,264],"major":[222],"issues":[223,266],"with":[224,249,255,279,632],"modern":[225],"technologies.":[228],"First,":[229],"requires":[232],"large":[233,386],"amount":[234],"labeled":[236,331],"an":[240,431,491],"model;":[242],"second,":[243],"network":[245,580],"architectures":[246,581],"that":[247,326,407,435,548,582,623],"work":[248,369],"not":[253,613],"proper":[254],"text.":[257,281,367],"In":[258,566],"this":[259,567],"thesis,":[260],"we":[261,463],"address":[262,464],"important":[265],"develop":[268],"four":[274],"supervised":[275],"unsupervised":[277],"present":[284],"feature":[287,352],"engineering":[288],"approach":[289,339],"informative":[291],"tweets":[292,321,332],"discovery":[293],"emerging":[296],"disasters.":[297],"propose":[299,570],"use":[301,314],"unlabeled":[302],"microblogs":[303],"cluster":[305],"words":[306,351],"limited":[309],"number":[310,329],"clusters":[312,317],"discovery.":[322],"results":[324],"indicate":[325],"100":[334],"or":[335,350],"less,":[336],"proposed":[338,409,625],"superior":[341,601],"standard":[344],"based":[346],"bag":[349],"representation.":[353],"introduce":[356],"human-in-the-loop":[358],"(HIL)":[359],"framework":[360,392,410,426,434],"identification":[363,395,404,429],"web":[366,397],"explores":[370],"ways":[371],"combine":[373],"expressive":[375],"power":[376],"REs,":[378],"ability":[379],"integrated":[391],"evaluation":[400],"several":[402],"problems":[405],"shows":[406],"achieves":[411],"high":[413],"accuracy":[414],"while":[415],"requiring":[416],"only":[417],"modest":[419],"human":[420,445],"involvement.":[421],"further":[423],"extend":[424],"iterative":[432,492],"HIL":[433],"addresses":[436],"recognition":[439],"problem.":[440],"particularly":[442],"investigate":[443],"how":[444],"invest":[446],"their":[447],"time":[448],"user":[451,512],"allowed":[453],"choose":[455],"between":[456],"regex":[457],"construction":[458],"manual":[460],"labeling.":[461],"Finally,":[462],"fundamental":[466],"problem":[467],"mining":[471],"domain,":[472],"i.e,":[473],"embedding":[474,484,488],"rare":[476],"out-of-vocabulary":[478],"(OOV)":[479],"words,":[480],"refining":[482],"models":[485,489],"character":[487],"way.":[493],"illustrate":[495],"simplicity":[497],"but":[498],"effectiveness":[499],"our":[501,624],"method":[502],"applying":[504],"online":[507],"professional":[508],"profiles":[509],"allowing":[510],"input.":[513],"Graph":[514],"shown":[519],"great":[520],"success":[521],"domain":[524],"drug":[526],"design":[527],"material":[529],"where":[531],"organic":[532],"molecules":[533,576],"crystal":[535],"structures":[536],"materials":[538],"represented":[540],"attributed":[542],"graphs.":[543,591],"A":[544],"architecture":[547],"capable":[550],"nodes":[555],"edges":[558],"crucial":[560],"property":[562],"estimation":[563],"molecules.":[565],"dissertation,":[568],"simple":[572,626],"representation":[574],"three":[578],"able":[584],"directly":[586],"predictive":[588],"functions":[589],"discover":[593],"that,":[594],"true":[597],"feature-driven":[603],"algorithms":[604],"formation":[606],"energy":[607],"prediction.":[608,619],"superiority":[611],"reproduced":[615],"band":[617],"gap":[618],"also":[621],"discovered":[622],"shallow":[627],"perform":[630],"comparably":[631],"state-of-the-art":[634],"networks.":[637]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-03-15T00:00:00"}