{"id":"https://openalex.org/W2901883903","doi":"https://doi.org/10.1109/iwcit.2019.8731626","title":"The Statistical Dictionary-Based String Matching Problem","display_name":"The Statistical Dictionary-Based String Matching Problem","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2901883903","doi":"https://doi.org/10.1109/iwcit.2019.8731626","mag":"2901883903"},"language":"en","primary_location":{"id":"doi:10.1109/iwcit.2019.8731626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcit.2019.8731626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Iran Workshop on Communication and Information Theory (IWCIT)","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/A5037570981","display_name":"M. Suri","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"M. Suri","raw_affiliation_strings":["Electrical and Computer Engineering Department, National Chiao Tung University (NCTU), Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, National Chiao Tung University (NCTU), Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067224441","display_name":"Stefano Rini","orcid":"https://orcid.org/0000-0003-1681-3316"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"S. Rini","raw_affiliation_strings":["Electrical and Computer Engineering Department, National Chiao Tung University (NCTU), Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, National Chiao Tung University (NCTU), Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9968000054359436,"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/T12029","display_name":"DNA and Biological Computing","score":0.996399998664856,"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":0.7326844930648804},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.729602038860321},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6895959377288818},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6867088675498962},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.6829918026924133},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.5594365000724792},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5453398823738098},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5295449495315552},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.49802136421203613},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.47995904088020325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46874314546585083},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.44208624958992004},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4245268702507019},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36826300621032715},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.32465556263923645},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.30692368745803833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22876620292663574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1886429786682129},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.12308856844902039},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11110609769821167},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08928167819976807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326844930648804},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.729602038860321},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6895959377288818},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6867088675498962},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6829918026924133},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.5594365000724792},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5453398823738098},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5295449495315552},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.49802136421203613},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47995904088020325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46874314546585083},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44208624958992004},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4245268702507019},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36826300621032715},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.32465556263923645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30692368745803833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22876620292663574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1886429786682129},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.12308856844902039},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11110609769821167},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08928167819976807},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcit.2019.8731626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcit.2019.8731626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Iran Workshop on Communication and Information Theory (IWCIT)","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":14,"referenced_works":["https://openalex.org/W9273873","https://openalex.org/W1484435918","https://openalex.org/W1569709403","https://openalex.org/W1660390307","https://openalex.org/W1858013062","https://openalex.org/W1902405276","https://openalex.org/W2022292926","https://openalex.org/W2055043387","https://openalex.org/W2064355379","https://openalex.org/W2117084652","https://openalex.org/W2152437528","https://openalex.org/W2263798363","https://openalex.org/W4236236547","https://openalex.org/W4301139523"],"related_works":["https://openalex.org/W2371263218","https://openalex.org/W2257399947","https://openalex.org/W3145288231","https://openalex.org/W2386746909","https://openalex.org/W2502807948","https://openalex.org/W2141423589","https://openalex.org/W2037600093","https://openalex.org/W2378689532","https://openalex.org/W2178786736","https://openalex.org/W2399644331"],"abstract_inverted_index":{"In":[0,64],"the":[1,20,36,41,48,54,55,60,67,80,87,90,97,101,114,118,122,127,130,134,138,152,156,160,167],"Dictionary-based":[2],"String":[3],"Matching":[4],"(DSM)":[5],"problem,":[6],"an":[7,141],"Information":[8],"Retrieval":[9],"(IR)":[10],"system":[11,120],"has":[12],"access":[13],"to":[14,58,150,174],"a":[15,23,29,33,39,74,93,107,170],"source":[16,49,88,144],"sequence":[17,50,103],"and":[18,76,89,177],"stores":[19],"position":[21,37],"of":[22,26,38,45,79,117,129,140,164,169],"certain":[24],"number":[25],"strings":[27,98,168],"in":[28,47,84,100,125,137,158],"posting":[30,56,102,131,135],"table.":[31],"When":[32],"user":[34],"inquires":[35],"string,":[40],"IR":[42,119],"system,":[43],"instead":[44],"searching":[46],"directly,":[51],"relies":[52],"on":[53],"table":[57],"answer":[59],"query":[61,91],"more":[62],"efficiently.":[63],"this":[65,110],"paper,":[66],"Statistical":[68],"DSM":[69,82],"problem":[70,83],"is":[71,148,162],"proposed":[72],"as":[73,106,121,175],"statistical":[75,94],"information-theoretic":[77],"formulation":[78,147],"classic":[81],"which":[85,159],"both":[86],"have":[92],"description":[95],"while":[96],"stored":[99],"are":[104],"described":[105],"code.":[108],"Through":[109],"formulation,":[111],"we":[112],"define":[113],"communication":[115,153],"efficiency":[116,154],"average":[123],"cost":[124],"retrieving":[126],"entries":[128],"list":[132],"from":[133],"table,":[136],"limit":[139],"infinitely":[142],"long":[143],"sequence.":[145],"This":[146],"used":[149],"study":[151],"for":[155],"case":[157],"dictionary":[161],"composed":[163],"(i)":[165],"all":[166],"given":[171],"length,":[172],"referred":[173],"k-grams,":[176],"(ii)":[178],"run-length":[179],"codes.":[180]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}