{"id":"https://openalex.org/W1600623192","doi":null,"title":"Graph-based weakly-supervised methods for information extraction & integration","display_name":"Graph-based weakly-supervised methods for information extraction & integration","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1600623192","mag":"1600623192"},"language":"en","primary_location":{"id":"pmh:oai:repository.upenn.edu:20.500.14332/6577","doi":null,"is_oa":false,"landing_page_url":"https://repository.upenn.edu/handle/20.500.14332/6577","pdf_url":null,"source":{"id":"https://openalex.org/S4306402083","display_name":"ScholarlyCommons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Dissertation/Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5102928374","display_name":"Fernando Pereira","orcid":"https://orcid.org/0009-0006-2360-1281","observed_orcids":["https://orcid.org/0009-0006-2360-1281"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fernando Pereira","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":"https://orcid.org/0009-0006-2360-1281","affiliations":[{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033696194","display_name":"Partha Pratim Talukdar","orcid":"https://orcid.org/0000-0001-8825-589X","observed_orcids":["https://orcid.org/0000-0001-8825-589X"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Partha Talukdar","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.5268999934196472,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.5268999934196472,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2087000012397766,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.10480000078678131,"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/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.9089999794960022},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.8949999809265137},{"id":"https://openalex.org/keywords/information-integration","display_name":"information integration","score":0.9980000257492065},{"id":"https://openalex.org/keywords/graph-learning","display_name":"graph learning","score":0.7509999871253967},{"id":"https://openalex.org/keywords/label-propagation","display_name":"label propagation","score":0.8920000195503235},{"id":"https://openalex.org/keywords/adsorption","display_name":"adsorption","score":0.8119999766349792},{"id":"https://openalex.org/keywords/schema-matching","display_name":"schema matching","score":0.6890000104904175},{"id":"https://openalex.org/keywords/query-construction","display_name":"query construction","score":0.41600000858306885},{"id":"https://openalex.org/keywords/interactive-feedback","display_name":"interactive feedback","score":0.640999972820282},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"knowledge base","score":0.7279999852180481},{"id":"https://openalex.org/keywords/schema-alignment","display_name":"schema alignment","score":0.3869999945163727},{"id":"https://openalex.org/keywords/foreign-keys","display_name":"foreign keys","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422762751579285},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.592468798160553},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5570628046989441},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.550740659236908},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5422900319099426},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5161341428756714},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4560132622718811},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.441845178604126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.394111692905426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3448994755744934},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3266501724720001},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19940543174743652},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14325383305549622}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:repository.upenn.edu:20.500.14332/6577","doi":null,"is_oa":false,"landing_page_url":"https://repository.upenn.edu/handle/20.500.14332/6577","pdf_url":null,"source":{"id":"https://openalex.org/S4306402083","display_name":"ScholarlyCommons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Dissertation/Thesis"},{"id":"mag:1600623192","doi":null,"is_oa":false,"landing_page_url":"http://www.talukdar.net/thesis/partha_thesis.pdf","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":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":123,"referenced_works":["https://openalex.org/W90502410","https://openalex.org/W130850236","https://openalex.org/W194033037","https://openalex.org/W197270748","https://openalex.org/W1479807131","https://openalex.org/W1493490255","https://openalex.org/W1499673022","https://openalex.org/W1506342804","https://openalex.org/W1519573073","https://openalex.org/W1539585011","https://openalex.org/W1552297528","https://openalex.org/W1552694902","https://openalex.org/W1597031998","https://openalex.org/W1630959083","https://openalex.org/W1660390307","https://openalex.org/W1781113593","https://openalex.org/W1905066734","https://openalex.org/W1971676915","https://openalex.org/W1973828215","https://openalex.org/W1975870392","https://openalex.org/W1981585544","https://openalex.org/W1984407615","https://openalex.org/W2007352552","https://openalex.org/W2008620264","https://openalex.org/W2008896880","https://openalex.org/W2011039300","https://openalex.org/W2011282943","https://openalex.org/W2020586530","https://openalex.org/W2022166150","https://openalex.org/W2038281398","https://openalex.org/W2047032662","https://openalex.org/W2051582400","https://openalex.org/W2056021151","https://openalex.org/W2056451646","https://openalex.org/W2057052429","https://openalex.org/W2059268928","https://openalex.org/W2063395464","https://openalex.org/W2066636486","https://openalex.org/W2068362339","https://openalex.org/W2068737686","https://openalex.org/W2069897123","https://openalex.org/W2078686663","https://openalex.org/W2082564813","https://openalex.org/W2083598336","https://openalex.org/W2084538728","https://openalex.org/W2086240273","https://openalex.org/W2087556608","https://openalex.org/W2088762045","https://openalex.org/W2098388305","https://openalex.org/W2098571317","https://openalex.org/W2099283723","https://openalex.org/W2099797738","https://openalex.org/W2100408869","https://openalex.org/W2100935296","https://openalex.org/W2103296194","https://openalex.org/W2103931177","https://openalex.org/W2107008379","https://openalex.org/W2107105629","https://openalex.org/W2108223890","https://openalex.org/W2108572131","https://openalex.org/W2110914363","https://openalex.org/W2111284344","https://openalex.org/W2111557120","https://openalex.org/W2113970290","https://openalex.org/W2116469285","https://openalex.org/W2116544254","https://openalex.org/W2117030594","https://openalex.org/W2117510361","https://openalex.org/W2119598708","https://openalex.org/W2120814856","https://openalex.org/W2122483056","https://openalex.org/W2122837498","https://openalex.org/W2123390832","https://openalex.org/W2123853152","https://openalex.org/W2125332694","https://openalex.org/W2125838338","https://openalex.org/W2128964720","https://openalex.org/W2130878769","https://openalex.org/W2132346211","https://openalex.org/W2132655161","https://openalex.org/W2133108446","https://openalex.org/W2133232758","https://openalex.org/W2134755874","https://openalex.org/W2136504847","https://openalex.org/W2137023796","https://openalex.org/W2138288827","https://openalex.org/W2138627627","https://openalex.org/W2139135093","https://openalex.org/W2139230981","https://openalex.org/W2139823104","https://openalex.org/W2143296986","https://openalex.org/W2144578941","https://openalex.org/W2147880316","https://openalex.org/W2148540243","https://openalex.org/W2148738951","https://openalex.org/W2150365753","https://openalex.org/W2153508518","https://openalex.org/W2154268919","https://openalex.org/W2154724067","https://openalex.org/W2156454791","https://openalex.org/W2156543375","https://openalex.org/W2157110051","https://openalex.org/W2158049734","https://openalex.org/W2160218441","https://openalex.org/W2161569281","https://openalex.org/W2163302275","https://openalex.org/W2163812767","https://openalex.org/W2165744911","https://openalex.org/W2169624745","https://openalex.org/W2171874178","https://openalex.org/W2172222998","https://openalex.org/W2172251087","https://openalex.org/W2173213060","https://openalex.org/W2201552871","https://openalex.org/W2293299776","https://openalex.org/W2293997450","https://openalex.org/W2300534015","https://openalex.org/W2328908889","https://openalex.org/W2336259629","https://openalex.org/W2538492099","https://openalex.org/W2891212941","https://openalex.org/W2913389685","https://openalex.org/W2953149585"],"related_works":["https://openalex.org/W2132679783","https://openalex.org/W7098392535","https://openalex.org/W4213351106","https://openalex.org/W1981266974","https://openalex.org/W2898700358","https://openalex.org/W2997873428","https://openalex.org/W2092919065","https://openalex.org/W3003599648","https://openalex.org/W157856073","https://openalex.org/W317603695"],"abstract_inverted_index":{"The":[0,237],"variety":[1],"and":[2,39,63,78,97,137,158,169,178,185,246,283,300,350,365,382,406],"complexity":[3],"of":[4,42,57,86,93,109,116,123,167,194,214,233,239,271,401],"potentially-related":[5],"data":[6,14,44,89,168],"resources":[7],"available":[8,329],"for":[9,128,156,181,253,377,425],"querying":[10],"---":[11,16],"webpages,":[12],"databases,":[13],"warehouses":[15],"has":[17,52,422],"been":[18,54,423],"growing":[19,26],"ever":[20],"more":[21],"rapidly.":[22],"There":[23],"is":[24,243,251,394],"a":[25,83,203,261,292,340,354],"need":[27,127,414],"to":[28,45,105,135,139,198,208,267,352,415],"pose":[29],"integrative":[30],"queries":[31,359],"across":[32,111],"multiple":[33],"such":[34,172,225],"sources,":[35,77,112],"exploiting":[36],"foreign":[37],"keys":[38],"other":[40],"means":[41],"interlinking":[43],"merge":[46],"information":[47,374,384],"from":[48,149,224,281,347],"diverse":[49,87],"sources.":[50,90],"This":[51,126,411],"traditionally":[53],"the":[55,94,106,121,192,317,399,413],"focus":[56,190],"research":[58],"within":[59],"Information":[60,64,183,336],"Extraction":[61,184],"(IE)":[62],"Integration":[65],"(II)":[66],"communities,":[67],"with":[68],"IE":[69,96,157],"focusing":[70,80],"on":[71,81,191,288,304,361,368],"converting":[72],"unstructured":[73,282],"sources":[74,381],"into":[75],"structured":[76,88,284],"II":[79,98],"providing":[82],"unified":[84],"view":[85],"However,":[91],"most":[92,426],"current":[95],"methods,":[99],"which":[100,250,344,421],"can":[101,174,229,321],"potentially":[102],"be":[103,322],"applied":[104],"pro":[107],"blem":[108],"integration":[110],"require":[113],"large":[114],"amounts":[115],"human":[117,151],"supervision,":[118],"often":[119,244],"in":[120,176,248,316,330,385,397,407],"form":[122],"annotated":[124],"data.":[125],"extensive":[129],"supervision":[130],"makes":[131],"existing":[132],"methods":[133,155,180],"expensive":[134,418],"deploy":[136],"difficult":[138],"maintain.":[140],"In":[141,160],"this":[142],"thesis,":[143],"we":[144,162,189,201,290,309,338],"develop":[145,202,339,416],"techniques":[146],"that":[147,164,221,390],"generalize":[148],"limited":[150],"input,":[152],"via":[153],"weakly-supervised":[154],"II.":[159],"particular,":[161],"argue":[163],"graph-based":[165,318],"representation":[166],"learning":[170,349,392],"over":[171],"graphs":[173],"result":[175],"effective":[177,396],"scalable":[179],"large-scale":[182],"Integration.":[186],"Within":[187,335],"IE,":[188],"problem":[193],"assigning":[195],"semantic":[196,216,327],"classes":[197],"entities.":[199],"First":[200],"context":[204],"pattern":[205],"induction":[206],"method":[207],"extend":[209],"small":[210],"initial":[211,273],"entity":[212,227],"lists":[213,228],"various":[215,305],"classes.":[217],"We":[218,258,370,387],"also":[219,310,371,388],"demonstrate":[220,301,389],"features":[222],"derived":[223],"extended":[226],"significantly":[230,268],"improve":[231],"performance":[232,315],"state-of-the-art":[234],"discriminative":[235],"taggers.":[236],"output":[238],"pattern-based":[240,276],"class-instance":[241,313],"extractors":[242],"high-precision":[245],"low-recall":[247,275],"nature,":[249],"inadequate":[252],"many":[254],"real":[255],"world":[256],"applications.":[257],"use":[259],"Adsorption,":[260,289],"graph":[262],"based":[263,360],"label":[264,294],"propagation":[265,295],"algorithm,":[266,296],"increase":[269],"recall":[270],"an":[272,373,417],"high-precision,":[274],"extractor":[277],"by":[278,324],"combining":[279,398],"evidences":[280],"text":[285],"corpora.":[286],"Building":[287],"propose":[291],"new":[293,380],"Modified":[297],"Adsorption":[298],"(MAD),":[299],"its":[302],"effectiveness":[303],"real-world":[306],"datasets.":[307],"Additionally,":[308],"show":[311],"how":[312],"acquisition":[314],"SSL":[319],"setting":[320],"improved":[323],"incorporating":[325,379],"additional":[326],"constraints":[328],"independently":[331],"developed":[332],"knowledge":[333],"bases.":[334],"Integration,":[337],"novel":[341],"system,":[342],"Q,":[343],"draws":[345],"ideas":[346],"machine":[348],"databases":[351],"help":[353],"non-expert":[355],"user":[356],"construct":[357],"data-integrating":[358],"keywords":[362],"(across":[363],"databases)":[364],"interactive":[366],"feedback":[367],"answers.":[369],"present":[372],"need-driven":[375],"strategy":[376,393],"automatically":[378],"their":[383],"Q.":[386],"Q's":[391],"highly":[395],"outputs":[400],"``black":[402],"box''":[403],"schema":[404,420],"matchers":[405],"re-weighting":[408],"bad":[409],"alignments.":[410],"removes":[412],"mediated":[419],"necessary":[424],"previous":[427],"systems.":[428]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}