{"id":"https://openalex.org/W2264424170","doi":"https://doi.org/10.1145/2716321","title":"Cost-Effective Conceptual Design for Information Extraction","display_name":"Cost-Effective Conceptual Design for Information Extraction","publication_year":2015,"publication_date":"2015-06-30","ids":{"openalex":"https://openalex.org/W2264424170","doi":"https://doi.org/10.1145/2716321","mag":"2264424170"},"language":"en","primary_location":{"id":"doi:10.1145/2716321","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716321","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-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/A5008664449","display_name":"Arash Termehchy","orcid":"https://orcid.org/0009-0007-2213-6303"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arash Termehchy","raw_affiliation_strings":["Oregon State University, OR"],"affiliations":[{"raw_affiliation_string":"Oregon State University, OR","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052582756","display_name":"Ali Vakilian","orcid":"https://orcid.org/0000-0001-5049-7594"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Vakilian","raw_affiliation_strings":["MIT, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068857843","display_name":"Yodsawalai Chodpathumwan","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yodsawalai Chodpathumwan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011314280","display_name":"Marianne Winslett","orcid":"https://orcid.org/0000-0002-3935-7168"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marianne Winslett","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008664449"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17244123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"2","first_page":"1","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T11106","display_name":"Data Management and Algorithms","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.8485392332077026},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6851579546928406},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.575835645198822},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.5239198803901672},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46469470858573914},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4611717760562897},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42127394676208496},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3695179224014282},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3404543697834015},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2955048680305481},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19643664360046387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09643945097923279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485392332077026},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6851579546928406},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.575835645198822},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.5239198803901672},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46469470858573914},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4611717760562897},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42127394676208496},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3695179224014282},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3404543697834015},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2955048680305481},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19643664360046387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09643945097923279},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2716321","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716321","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W147286453","https://openalex.org/W157725869","https://openalex.org/W197270748","https://openalex.org/W1480376833","https://openalex.org/W1484025826","https://openalex.org/W1491206589","https://openalex.org/W1532325895","https://openalex.org/W1540618313","https://openalex.org/W1542883217","https://openalex.org/W1569403765","https://openalex.org/W1601433541","https://openalex.org/W1607797725","https://openalex.org/W1695350145","https://openalex.org/W1854444541","https://openalex.org/W1968922864","https://openalex.org/W1972300623","https://openalex.org/W1978486030","https://openalex.org/W1982912896","https://openalex.org/W2012910912","https://openalex.org/W2017279302","https://openalex.org/W2024980584","https://openalex.org/W2026469784","https://openalex.org/W2026891055","https://openalex.org/W2035840394","https://openalex.org/W2045463753","https://openalex.org/W2049711652","https://openalex.org/W2069140227","https://openalex.org/W2088403135","https://openalex.org/W2093808275","https://openalex.org/W2096891167","https://openalex.org/W2097802284","https://openalex.org/W2099868020","https://openalex.org/W2103224511","https://openalex.org/W2104896715","https://openalex.org/W2105588112","https://openalex.org/W2116066543","https://openalex.org/W2124044117","https://openalex.org/W2144416276","https://openalex.org/W2145111356","https://openalex.org/W2148726341","https://openalex.org/W2151192680","https://openalex.org/W2156454791","https://openalex.org/W2157952725","https://openalex.org/W2163072729","https://openalex.org/W2165657574","https://openalex.org/W2169463693","https://openalex.org/W2170995957","https://openalex.org/W2171806843","https://openalex.org/W2251214202","https://openalex.org/W2293072638","https://openalex.org/W2406996511","https://openalex.org/W2913389685","https://openalex.org/W2964068340","https://openalex.org/W4298304654"],"related_works":["https://openalex.org/W2891776881","https://openalex.org/W2244559970","https://openalex.org/W2557467218","https://openalex.org/W2536297025","https://openalex.org/W2771290394","https://openalex.org/W2918080139","https://openalex.org/W3130064765","https://openalex.org/W3204684126","https://openalex.org/W2618582729","https://openalex.org/W2001068920"],"abstract_inverted_index":{"It":[0],"is":[1,32,144,193,233],"well":[2],"established":[3],"that":[4,120,203,261],"extracting":[5],"and":[6,38,73,91,109,141,172,231,246,259,263],"annotating":[7],"occurrences":[8],"of":[9,14,24,47,68,96,106,125,138,150,190,256,306],"entities":[10],"in":[11,147,273],"a":[12,66,79,102,104,110,117,162,194,215,227,234,243,247],"collection":[13,245,311],"unstructured":[15],"text":[16],"documents":[17],"with":[18],"their":[19],"concepts":[20,70,207,221,284,293],"improves":[21,122],"the":[22,28,44,83,94,123,129,139,148,160,188,205,211,220,253,257,277,282,291,297,304,310,314],"effectiveness":[23,124,305],"answering":[25,126,307],"queries":[26,127,308],"over":[27,128,309],"collection.":[29,85,130],"However,":[30],"it":[31,60,143],"very":[33],"resource":[34],"intensive":[35],"to":[36,63,115,158],"create":[37],"maintain":[39],"large":[40],"annotated":[41,84],"collections.":[42],"Since":[43],"available":[45],"resources":[46],"an":[48,165],"enterprise":[49],"are":[50,184,208,222,285,294],"limited":[51],"and/or":[52],"its":[53],"users":[54],"may":[55,61],"have":[56,62],"urgent":[57],"information":[58],"needs,":[59],"select":[64],"only":[65],"subset":[67,78],"relevant":[69,107,151,206,283,292],"for":[71,82,135,170,177],"extraction":[72],"annotation.":[74],"We":[75,131,153,179,200],"call":[76],"this":[77,87],"conceptual":[80,98,118,267,279,298],"design":[81,99,119],"In":[86],"article,":[88],"we":[89],"introduce":[90],"formally":[92],"define":[93],"problem":[95,140,258],"cost-effective":[97],"where,":[100],"given":[101],"collection,":[103],"set":[105],"concepts,":[108,191],"fixed":[111],"budget,":[112],"one":[113],"likes":[114],"find":[116],"most":[121],"provide":[132],"efficient":[133,156],"algorithms":[134],"special":[136],"cases":[137],"prove":[142,202],"generally":[145],"NP-hard":[146],"number":[149],"concepts.":[152],"propose":[154],"three":[155],"approximations":[157],"solve":[159],"problem:":[161],"greedy":[163,212],"algorithm,":[164],"approximate":[166,173],"popularity":[167],"maximization":[168,175],"(APM":[169],"short),":[171],"annotation-benefit":[174],"(AAM":[176],"short).":[178],"show":[180,260],"that,":[181,272],"if":[182,204,219,281,290],"there":[183],"no":[185],"constraints":[186],"regrading":[187],"overlap":[189],"APM":[192,225,262,275],"fully":[195,235],"polynomial":[196],"time":[197],"approximation":[198,217,229,237],"scheme.":[199,238],"also":[201,270],"mutually":[209,287,295],"exclusive,":[210,296],"algorithm":[213],"delivers":[214,276],"constant":[216,228],"ratio":[218],"equally":[223],"costly,":[224],"has":[226],"ratio,":[230],"AAM":[232,264,302],"polynomial-time":[236],"Our":[239],"empirical":[240],"results":[241],"using":[242],"Wikipedia":[244],"search":[248],"engine":[249],"query":[250],"log":[251],"validate":[252],"proposed":[254],"formalization":[255],"efficiently":[265],"compute":[266],"designs.":[268],"They":[269],"indicate":[271],"general,":[274],"optimal":[278],"designs":[280,299],"not":[286],"exclusive.":[288],"Also,":[289],"delivered":[300],"by":[301,317],"improve":[303],"more":[312],"than":[313],"solutions":[315],"provided":[316],"APM.":[318]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}