{"id":"https://openalex.org/W2016587141","doi":"https://doi.org/10.1109/asap.2013.6567551","title":"A high-speed and large-scale dictionary matching engine for Information Extraction systems","display_name":"A high-speed and large-scale dictionary matching engine for Information Extraction systems","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W2016587141","doi":"https://doi.org/10.1109/asap.2013.6567551","mag":"2016587141"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2013.6567551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2013.6567551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors","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/A5113938530","display_name":"Kanak Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kanak Agarwal","raw_affiliation_strings":["Austin Research Laboratory, IBM Corporation, Austin, TX, USA","Austin Research Lab, IBM Corp., Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Austin Research Laboratory, IBM Corporation, Austin, TX, USA","institution_ids":["https://openalex.org/I4210156936"]},{"raw_affiliation_string":"Austin Research Lab, IBM Corp., Austin, TX, USA","institution_ids":["https://openalex.org/I4210156936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026275592","display_name":"Raphael Polig","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Raphael Polig","raw_affiliation_strings":["Zurich Research Laboratory, IBM Corporation, Zurich, Switzerland","Zurich Res. Lab., IBM Corp., Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Zurich Research Laboratory, IBM Corporation, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]},{"raw_affiliation_string":"Zurich Res. Lab., IBM Corp., Zurich, Switzerland","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113938530"],"corresponding_institution_ids":["https://openalex.org/I4210156936"],"apc_list":null,"apc_paid":null,"fwci":0.4809,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75173974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"37","issue":null,"first_page":"59","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12029","display_name":"DNA and Biological Computing","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.863365650177002},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.7753766775131226},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6112147569656372},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5743024349212646},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5581364631652832},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.5528796911239624},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.4772063195705414},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.46772778034210205},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4638509750366211},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.45074349641799927},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4457100033760071},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4443865120410919},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41362887620925903},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3264960050582886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20921552181243896},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14579710364341736},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11191785335540771}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.863365650177002},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.7753766775131226},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6112147569656372},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5743024349212646},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5581364631652832},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.5528796911239624},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4772063195705414},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.46772778034210205},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4638509750366211},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.45074349641799927},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4457100033760071},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4443865120410919},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41362887620925903},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3264960050582886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20921552181243896},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14579710364341736},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11191785335540771},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2013.6567551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2013.6567551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1710586424","https://openalex.org/W1911613893","https://openalex.org/W1965663430","https://openalex.org/W1972418517","https://openalex.org/W1985108724","https://openalex.org/W2014959658","https://openalex.org/W2099479059","https://openalex.org/W2099964107","https://openalex.org/W2110367654","https://openalex.org/W2115775347","https://openalex.org/W2118599039","https://openalex.org/W2118681606","https://openalex.org/W2134826720","https://openalex.org/W2135932040","https://openalex.org/W2913389685","https://openalex.org/W6637563156","https://openalex.org/W6641419589"],"related_works":["https://openalex.org/W3145288231","https://openalex.org/W2371263218","https://openalex.org/W86797766","https://openalex.org/W2021357933","https://openalex.org/W2504957479","https://openalex.org/W1774017438","https://openalex.org/W1492858093","https://openalex.org/W2092552144","https://openalex.org/W3216580934","https://openalex.org/W1980331464"],"abstract_inverted_index":{"Dictionary":[0],"matching":[1,14,45,133],"is":[2,80],"a":[3,15,20,23,33,58,97,118,141],"commonly":[4,65],"used":[5,66],"operation":[6],"in":[7,19],"Information":[8],"Extraction":[9],"(IE)":[10],"systems.":[11],"It":[12],"involves":[13],"set":[16],"of":[17,25,64,75,144],"strings":[18],"document":[21,138],"against":[22],"dictionary":[24,44,132,154],"pre-defined":[26],"patterns.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"describe":[32],"high":[34,42],"performance":[35],"and":[36],"scalable":[37],"hardware":[38,55,131],"architecture":[39],"to":[40,158],"enable":[41],"throughput":[43,107],"on":[46,117,121],"very":[47,164],"large":[48,153],"dictionaries":[49],"for":[50,152,166],"text":[51],"analytics":[52],"applications.":[53],"Our":[54,113],"accelerator":[56],"employs":[57],"novel":[59],"hashing":[60],"based":[61,71,78,93,111,116],"approach":[62],"instead":[63],"deterministic":[67],"finite":[68],"automata":[69],"(DFA)":[70],"algorithms.":[72],"A":[73],"limitation":[74],"the":[76,90,109],"DFA":[77,110],"approaches":[79],"that":[81,129],"they":[82],"typically":[83],"process":[84,96,136],"one":[85],"character":[86],"every":[87,100],"cycle,":[88,101],"while":[89,148],"proposed":[91],"hash":[92],"scheme":[94],"can":[95,135],"string":[98],"token":[99],"thus":[102,161],"achieving":[103],"significantly":[104],"higher":[105],"processing":[106,142],"than":[108],"implementations.":[112],"measurement":[114],"results":[115],"prototype":[119],"implementation":[120],"an":[122],"Altera":[123],"Stratix":[124],"IV":[125],"FPGA":[126],"device":[127],"indicate":[128],"our":[130],"engine":[134],"typical":[137],"streams":[139],"at":[140],"rate":[143],"~1.5GB/s":[145],"(~12":[146],"Gbps)":[147],"simultaneously":[149],"allowing":[150],"support":[151],"sizes":[155],"containing":[156],"up":[157],"~100K":[159],"patterns,":[160],"making":[162],"it":[163],"useful":[165],"IE":[167],"workload":[168],"acceleration.":[169]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
