{"id":"https://openalex.org/W2584402701","doi":"https://doi.org/10.1109/bigdata.2016.7840617","title":"Entity resolution acceleration using the automata processor","display_name":"Entity resolution acceleration using the automata processor","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2584402701","doi":"https://doi.org/10.1109/bigdata.2016.7840617","mag":"2584402701"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069515104","display_name":"Chunkun Bo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunkun Bo","raw_affiliation_strings":["Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005572542","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-0474-0183"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070390660","display_name":"Jeffrey J. Fox","orcid":"https://orcid.org/0000-0002-3780-4956"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey J. Fox","raw_affiliation_strings":["Department of Material Science, University of Virginia, Charlottesville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Material Science, University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074818897","display_name":"Kevin Skadron","orcid":"https://orcid.org/0000-0002-8091-9302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Skadron","raw_affiliation_strings":["Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3487,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9734993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9718000292778015,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9509000182151794,"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/bottleneck","display_name":"Bottleneck","score":0.8741262555122375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8293484449386597},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.629371166229248},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5204934477806091},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4691274166107178},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4667907655239105},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4568711817264557},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.4387499690055847},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.42349088191986084},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.41892209649086},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.39994049072265625},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3611491322517395},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3298228979110718},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31318485736846924},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23552268743515015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19556182622909546},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16772979497909546},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.12901052832603455}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8741262555122375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293484449386597},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.629371166229248},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5204934477806091},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4691274166107178},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4667907655239105},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4568711817264557},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.4387499690055847},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.42349088191986084},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.41892209649086},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.39994049072265625},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3611491322517395},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3298228979110718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31318485736846924},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23552268743515015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19556182622909546},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16772979497909546},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.12901052832603455}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1503428008","https://openalex.org/W1521294226","https://openalex.org/W1569123402","https://openalex.org/W2024770506","https://openalex.org/W2040976214","https://openalex.org/W2042913039","https://openalex.org/W2044242345","https://openalex.org/W2062949766","https://openalex.org/W2079971532","https://openalex.org/W2117974736","https://openalex.org/W2123561513","https://openalex.org/W4254788633","https://openalex.org/W6633966005"],"related_works":["https://openalex.org/W2371263218","https://openalex.org/W1651353716","https://openalex.org/W2616198066","https://openalex.org/W2257399947","https://openalex.org/W3145288231","https://openalex.org/W2037600093","https://openalex.org/W2399644331","https://openalex.org/W2386746909","https://openalex.org/W2178786736","https://openalex.org/W2141423589"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER),":[2],"the":[3,24,51,85,109],"process":[4],"of":[5,20,88],"finding":[6],"identical":[7,33],"entities":[8,34],"across":[9,41],"different":[10,100,134],"databases,":[11],"is":[12,50],"critical":[13],"to":[14,31,103],"many":[15],"information-integration":[16],"applications.":[17],"As":[18],"sizes":[19],"databases":[21],"explode":[22],"in":[23],"big-data":[25],"era,":[26],"it":[27],"becomes":[28],"computationally":[29],"expensive":[30],"recognize":[32],"among":[35],"all":[36],"records":[37],"with":[38,112],"variations":[39],"allowed":[40],"multiple":[42],"databases.":[43],"Profiling":[44],"results":[45],"show":[46],"that":[47],"approximate":[48],"matching":[49,90],"primary":[52],"bottleneck.":[53],"The":[54],"Automata":[55],"Processor":[56],"(AP),":[57],"an":[58,79],"efficient":[59],"and":[60,97,116,121,127],"scalable":[61],"semiconductor":[62],"architecture":[63],"for":[64,72,75,91,133],"parallel":[65],"automata":[66],"processing,":[67],"provides":[68],"a":[69],"new":[70],"opportunity":[71],"hardware":[73],"acceleration":[74],"ER.":[76],"We":[77,107],"propose":[78],"AP-accelerated":[80],"ER":[81],"solution,":[82],"which":[83],"accelerates":[84],"performance":[86],"bottleneck":[87],"fuzzy":[89],"similar":[92],"but":[93],"potentially":[94],"inexactly-matched":[95],"names,":[96],"use":[98],"several":[99,113],"real-world":[101],"applications":[102],"illustrate":[104],"its":[105],"effectiveness.":[106],"compared":[108],"proposed":[110],"method":[111],"conventional":[114],"methods":[115],"achieved":[117],"both":[118],"promising":[119],"speedups":[120],"better":[122],"accuracy":[123],"(more":[124],"correct":[125],"pairs":[126],"less":[128],"generalized":[129],"merge":[130],"distance":[131],"cost)":[132],"datasets.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}