{"id":"https://openalex.org/W2139660688","doi":"https://doi.org/10.1145/1989323.1989379","title":"Faerie","display_name":"Faerie","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2139660688","doi":"https://doi.org/10.1145/1989323.1989379","mag":"2139660688"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 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/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Deng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100951661","display_name":"Jianhua Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Feng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100451576"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":8.1944,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97633574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"529","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9933000206947327,"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":0.9915000200271606,"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/jaccard-index","display_name":"Jaccard index","score":0.8934527635574341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8037177920341492},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.684105396270752},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.67267906665802},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5638114213943481},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5606684684753418},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.5348395705223083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4975595772266388},{"id":"https://openalex.org/keywords/longest-common-subsequence-problem","display_name":"Longest common subsequence problem","score":0.4947199523448944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42001405358314514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3499031662940979},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3463134765625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17072930932044983},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.15731248259544373}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8934527635574341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037177920341492},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.684105396270752},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.67267906665802},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5638114213943481},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5606684684753418},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.5348395705223083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975595772266388},{"id":"https://openalex.org/C120098539","wikidata":"https://www.wikidata.org/wiki/Q141001","display_name":"Longest common subsequence problem","level":2,"score":0.4947199523448944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42001405358314514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3499031662940979},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3463134765625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17072930932044983},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.15731248259544373},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1989323.1989379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W125979907","https://openalex.org/W1578664299","https://openalex.org/W1974995373","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2098571654","https://openalex.org/W2099370490","https://openalex.org/W2100235843","https://openalex.org/W2105423800","https://openalex.org/W2105436061","https://openalex.org/W2113618143","https://openalex.org/W2115215982","https://openalex.org/W2119057313","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2129598390","https://openalex.org/W2131815873","https://openalex.org/W2147033904","https://openalex.org/W2150916025","https://openalex.org/W2159491434","https://openalex.org/W2161936973","https://openalex.org/W2166804299","https://openalex.org/W2167029568","https://openalex.org/W2167847032","https://openalex.org/W6674576723","https://openalex.org/W6675190639","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2950594955","https://openalex.org/W2520870971","https://openalex.org/W1989944203","https://openalex.org/W2775696757","https://openalex.org/W4387083800","https://openalex.org/W4385963882","https://openalex.org/W1998479724","https://openalex.org/W2136519138","https://openalex.org/W2546839375","https://openalex.org/W4381948805"],"abstract_inverted_index":{"Dictionary-based":[0],"entity":[1,25],"extraction":[2,19],"identifies":[3],"predefined":[4],"entities":[5,37],"(e.g.,":[6,52,58],"person":[7],"names":[8],"or":[9,55],"locations)":[10],"from":[11],"a":[12,39,64,73,118],"document.":[13],"A":[14],"recent":[15],"trend":[16],"for":[17,63],"improving":[18],"recall":[20],"is":[21],"to":[22,44,67,100,108,121,144,154],"support":[23,48,68,122],"approximate":[24],"extraction,":[26],"which":[27],"finds":[28],"all":[29],"substrings":[30,89],"in":[31,38,90],"the":[32,78,84,91,102,106,146,156],"document":[33,92],"that":[34,162],"approximately":[35],"match":[36],"given":[40],"dictionary.":[41],"Existing":[42],"methods":[43],"address":[45],"this":[46,114],"problem":[47],"either":[49],"token-based":[50],"similarity":[51],"Jaccard":[53],"Similarity)":[54],"character-based":[56],"dissimilarity":[57],"Edit":[59],"Distance).":[60],"It":[61],"calls":[62],"unified":[65,74,119],"method":[66,75,164],"various":[69],"similarity/dissimilarity":[70,124],"functions,":[71,125],"since":[72],"can":[76],"reduce":[77],"programming":[79],"efforts,":[80],"hardware":[81],"requirements,":[82],"and":[83,95,136,149,168],"manpower.":[85],"In":[86,113],"addition,":[87],"many":[88,123],"have":[93,97],"overlaps,":[94],"we":[96,116],"an":[98],"opportunity":[99],"utilize":[101,145],"shared":[103,147],"computation":[104,148],"across":[105],"overlaps":[107],"avoid":[109],"unnecessary":[110],"redundant":[111],"computation.":[112],"paper,":[115],"propose":[117],"framework":[120],"such":[126],"as":[127],"jaccard":[128],"similarity,":[129,131,133,135],"cosine":[130],"dice":[132],"edit":[134,137],"distance.":[138],"We":[139],"devise":[140],"efficient":[141],"filtering":[142],"algorithms":[143],"develop":[150],"effective":[151],"pruning":[152],"techniques":[153],"improve":[155],"performance.":[157],"The":[158],"experimental":[159],"results":[160],"show":[161],"our":[163],"achieves":[165],"high":[166],"performance":[167],"outperforms":[169],"state-of-the-art":[170],"studies.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}