{"id":"https://openalex.org/W2097549659","doi":"https://doi.org/10.1109/itw.2005.1531901","title":"String parsing-based similarity detection","display_name":"String parsing-based similarity detection","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2097549659","doi":"https://doi.org/10.1109/itw.2005.1531901","mag":"2097549659"},"language":"en","primary_location":{"id":"doi:10.1109/itw.2005.1531901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2005.1531901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Information Theory Workshop, 2005.","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":null,"display_name":"J. Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"J. Yang","raw_affiliation_strings":["Department of Computer Science, University of Auckland, Auckland, New Zealand","Dept of Computer Science, Auckland University, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Dept of Computer Science, Auckland University, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072582772","display_name":"Ulrich Speidel","orcid":"https://orcid.org/0000-0001-9107-4918"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"U. Speidel","raw_affiliation_strings":["Department of Computer Science, University of Auckland, Auckland, New Zealand","Dept of Computer Science, Auckland University, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]},{"raw_affiliation_string":"Dept of Computer Science, Auckland University, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.12940206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"259","issue":null,"first_page":"5 pp.","last_page":"5 pp."},"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/T11567","display_name":"semigroups and automata theory","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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/parsing","display_name":"Parsing","score":0.8287726640701294},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.7949296236038208},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6910666823387146},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6424295902252197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6295137405395508},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6250774264335632},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.5631020665168762},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.5184018611907959},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5031644701957703},{"id":"https://openalex.org/keywords/hamming-weight","display_name":"Hamming weight","score":0.46634477376937866},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4517190456390381},{"id":"https://openalex.org/keywords/compromise","display_name":"Compromise","score":0.4447018504142761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4246048927307129},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4156331717967987},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38430315256118774},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3327869176864624},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2530614137649536},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.2339763343334198},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.07310393452644348}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8287726640701294},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.7949296236038208},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6910666823387146},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6424295902252197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295137405395508},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6250774264335632},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.5631020665168762},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.5184018611907959},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5031644701957703},{"id":"https://openalex.org/C63361517","wikidata":"https://www.wikidata.org/wiki/Q5645805","display_name":"Hamming weight","level":5,"score":0.46634477376937866},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4517190456390381},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.4447018504142761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4246048927307129},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4156331717967987},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38430315256118774},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3327869176864624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2530614137649536},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.2339763343334198},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.07310393452644348},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itw.2005.1531901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2005.1531901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Information Theory Workshop, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1529615245","https://openalex.org/W2008803097","https://openalex.org/W2014016891","https://openalex.org/W2062202510","https://openalex.org/W2077770566","https://openalex.org/W2086848345","https://openalex.org/W2107745473","https://openalex.org/W2120741727","https://openalex.org/W2122070588","https://openalex.org/W2122962290","https://openalex.org/W2157090926","https://openalex.org/W2611071497","https://openalex.org/W2911684292","https://openalex.org/W4234535213","https://openalex.org/W6666493864","https://openalex.org/W6678142254","https://openalex.org/W6683533716"],"related_works":["https://openalex.org/W2008960744","https://openalex.org/W2105471374","https://openalex.org/W2963549154","https://openalex.org/W2158117886","https://openalex.org/W1987803429","https://openalex.org/W1582340598","https://openalex.org/W1519122282","https://openalex.org/W2182731056","https://openalex.org/W2176368139","https://openalex.org/W2074967255"],"abstract_inverted_index":{"This":[0],"paper":[1],"compares":[2],"the":[3,12,16,23],"similarity-detection":[4],"abilities":[5],"of":[6,42],"two":[7],"string":[8],"parsing":[9],"algorithms":[10],"from":[11],"Lempel-Ziv":[13],"family":[14],"and":[15,25,33,57],"T-decomposition":[17,34,48],"algorithm":[18],"proposed":[19],"by":[20],"Titchener":[21],"against":[22],"Hamming":[24],"Levenshtein":[26],"measures.":[27],"Our":[28],"results":[29],"show":[30],"that":[31,47],"LZ":[32],"based":[35,49],"measures":[36,50],"work":[37],"in":[38],"a":[39,52],"wider":[40],"range":[41],"contexts.":[43],"We":[44],"also":[45],"argue":[46],"represent":[51],"good":[53],"compromise":[54],"between":[55],"accuracy":[56],"time":[58],"complexity.":[59]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}