{"id":"https://openalex.org/W2024980584","doi":"https://doi.org/10.1145/2588555.2610496","title":"Which concepts are worth extracting?","display_name":"Which concepts are worth extracting?","publication_year":2014,"publication_date":"2014-06-18","ids":{"openalex":"https://openalex.org/W2024980584","doi":"https://doi.org/10.1145/2588555.2610496","mag":"2024980584"},"language":"en","primary_location":{"id":"doi:10.1145/2588555.2610496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of 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/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, Corvallis, USA","Oregon State University, Corvallis, USA;"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Oregon State University, Corvallis, USA;","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 , USA"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge , USA","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/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yodsawalai Chodpathumwan","raw_affiliation_strings":["University of Illinois, Urbana, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana, USA","institution_ids":["https://openalex.org/I2801919071"]}]},{"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/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marianne Winslett","raw_affiliation_strings":["University of Illinois, Urbana, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana, USA","institution_ids":["https://openalex.org/I2801919071"]}]}],"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":2.4541,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91062781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"779","last_page":"790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9940000176429749,"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/T11106","display_name":"Data Management and Algorithms","score":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7855557799339294},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6932935118675232},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5638203024864197},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.539989709854126},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5128119587898254},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5095487236976624},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5079742074012756},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.44189831614494324},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3901740312576294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3390140235424042},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2199350893497467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19713711738586426},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18339860439300537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14106401801109314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7855557799339294},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6932935118675232},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5638203024864197},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.539989709854126},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5128119587898254},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5095487236976624},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5079742074012756},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.44189831614494324},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3901740312576294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3390140235424042},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2199350893497467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19713711738586426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18339860439300537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14106401801109314},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2588555.2610496","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.934.8775","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.934.8775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mit.edu/%7Evakilian/publication/concept-annotation-sigmod14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3370011401","display_name":null,"funder_award_id":"CNS-0716532","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G5707961779","display_name":null,"funder_award_id":"CCF-0938071","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G6649110404","display_name":null,"funder_award_id":"CCF-0938064","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W109634425","https://openalex.org/W142212369","https://openalex.org/W197270748","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/W1607797725","https://openalex.org/W1695350145","https://openalex.org/W1978486030","https://openalex.org/W1982912896","https://openalex.org/W2012910912","https://openalex.org/W2026891055","https://openalex.org/W2035840394","https://openalex.org/W2038901175","https://openalex.org/W2045463753","https://openalex.org/W2069140227","https://openalex.org/W2104896715","https://openalex.org/W2116066543","https://openalex.org/W2135087558","https://openalex.org/W2156454791","https://openalex.org/W2163072729","https://openalex.org/W2169463693","https://openalex.org/W2171806843","https://openalex.org/W2293072638","https://openalex.org/W2406996511","https://openalex.org/W6633961643","https://openalex.org/W7065312267"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W1570025324","https://openalex.org/W2116902754","https://openalex.org/W2166185180"],"abstract_inverted_index":{"It":[0],"is":[1,32,135,172,182,208],"well":[2],"established":[3],"that":[4,118,132,169,192,236,247],"extracting":[5],"and":[6,38,73,107,144,160,206,221,234,238],"annotating":[7],"occurrences":[8],"of":[9,14,24,47,68,93,104,122,141,179,231,281],"entities":[10],"in":[11,138,248],"a":[12,66,79,100,102,108,115,183,202,209,222],"collection":[13,127,220,286],"unstructured":[15],"text":[16],"documents":[17],"with":[18],"their":[19],"concepts":[20,70,143,196,259,268],"improve":[21,278],"the":[22,28,44,83,91,120,126,128,133,139,152,177,194,228,232,252,257,266,272,279,285,289],"effectiveness":[23,121,280],"answering":[25,123,282],"queries":[26,124,283],"over":[27,125,284],"collection.":[29,85],"However,":[30],"it":[31,60],"very":[33],"resource":[34],"intensive":[35],"to":[36,63,113,150],"create":[37],"maintain":[39],"large":[40],"annotated":[41,84],"collections.":[42],"Since":[43],"available":[45],"resources":[46],"an":[48],"enterprise":[49],"are":[50,197,260,269],"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":[69,105,142,195,258,267],"for":[71,82,158,165],"extraction":[72],"annotation.":[74],"We":[75,130,167,189],"call":[76],"this":[77,87],"conceptual":[80,96,116,242,254,273],"design":[81,117],"In":[86],"paper,":[88],"we":[89],"introduce":[90],"problem":[92,134,233],"cost":[94],"effective":[95],"design,":[97],"where":[98],"given":[99],"collection,":[101],"set":[103],"concepts,":[106,180],"fixed":[109],"budget,":[110],"one":[111],"likes":[112],"find":[114],"improves":[119],"most.":[129],"prove":[131,191],"generally":[136],"NP-hard":[137],"number":[140],"propose":[145],"two":[146],"efficient":[147],"approximation":[148,187,204,213],"algorithms":[149],"solve":[151],"problem:":[153],"Approximate":[154,161],"Popularity":[155],"Maximization":[156,163],"(APM":[157],"short)":[159],"Annotation-benefit":[162],"(AAM":[164],"short).":[166],"show":[168,235],"if":[170,193,256,265],"there":[171],"not":[173,261],"any":[174],"constraints":[175],"regrading":[176],"overlap":[178],"APM":[181,200,237,250],"fully":[184,210],"polynomial":[185,211],"time":[186,212],"scheme.":[188,214],"also":[190,245],"mutually":[198,262,270],"exclusive,":[199,271],"has":[201],"constant":[203],"ratio":[205],"AAM":[207,239,277],"Our":[215],"empirical":[216],"results":[217],"using":[218],"Wikipedia":[219],"search":[223],"engine":[224],"query":[225],"log":[226],"validate":[227],"proposed":[229],"formalization":[230],"efficiently":[240],"compute":[241],"designs.":[243],"They":[244],"indicate":[246],"general":[249],"delivers":[251],"optimal":[253],"designs":[255,274],"exclusive.":[263],"Also,":[264],"delivered":[275],"by":[276,292],"more":[287],"than":[288],"solutions":[290],"provided":[291],"APM.":[293]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}