{"id":"https://openalex.org/W2920798169","doi":"https://doi.org/10.5220/0007259200520063","title":"The Growing N-Gram Algorithm: A Novel Approach to String Clustering","display_name":"The Growing N-Gram Algorithm: A Novel Approach to String Clustering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2920798169","doi":"https://doi.org/10.5220/0007259200520063","mag":"2920798169"},"language":"en","primary_location":{"id":"doi:10.5220/0007259200520063","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007259200520063","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0007259200520063","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066171258","display_name":"Corrado Grappiolo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corrado Grappiolo","raw_affiliation_strings":["ESI (TNO), Eindhoven and The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESI (TNO), Eindhoven and The Netherlands, --- Select a Country ---","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060512147","display_name":"Eline Verwielen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eline Verwielen","raw_affiliation_strings":["Unaffiliated, Valkenswaard and The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unaffiliated, Valkenswaard and The Netherlands, --- Select a Country ---","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074953240","display_name":"Nils Noorman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122849","display_name":"Philips (Netherlands)","ror":"https://ror.org/02p2bgp27","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210122849"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nils Noorman","raw_affiliation_strings":["Philips Healthcare, Best and The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips Healthcare, Best and The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I4210122849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01634812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9973999857902527,"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/T11719","display_name":"Data Quality and Management","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8120185136795044},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7760597467422485},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7262076139450073},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.559120774269104},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5162220001220703},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4719511568546295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4708932042121887},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4378645718097687},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4287658929824829},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3706132769584656},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36084264516830444},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32404112815856934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08160901069641113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120185136795044},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7760597467422485},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7262076139450073},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.559120774269104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5162220001220703},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4719511568546295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708932042121887},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4378645718097687},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4287658929824829},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3706132769584656},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36084264516830444},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32404112815856934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08160901069641113},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0007259200520063","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007259200520063","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},{"id":"pmh:oai:oai-pmh.tno.nl:49368","is_oa":false,"landing_page_url":"https://resolver.tno.nl/uuid:700e740b-6c7f-4041-ba8a-93c3629007a9","pdf_url":null,"source":{"id":"https://openalex.org/S7407055233","display_name":"TNO Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:tudelft.nl:uuid:700e740b-6c7f-4041-ba8a-93c3629007a9","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:700e740b-6c7f-4041-ba8a-93c3629007a9","pdf_url":null,"source":{"id":"https://openalex.org/S4306402238","display_name":"Repository hosted by TU Delft Library (TU Delft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.5220/0007259200520063","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007259200520063","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W95524657","https://openalex.org/W148400104","https://openalex.org/W168564468","https://openalex.org/W1647671624","https://openalex.org/W1651093245","https://openalex.org/W1790954942","https://openalex.org/W1934041838","https://openalex.org/W1970014186","https://openalex.org/W1971784203","https://openalex.org/W1995872006","https://openalex.org/W1996764654","https://openalex.org/W2034190452","https://openalex.org/W2052351313","https://openalex.org/W2112721126","https://openalex.org/W2121227244","https://openalex.org/W2123406803","https://openalex.org/W2135716572","https://openalex.org/W2136061479","https://openalex.org/W2150376021","https://openalex.org/W2153579005","https://openalex.org/W2158195707","https://openalex.org/W2167528246","https://openalex.org/W2251410829","https://openalex.org/W2743596624","https://openalex.org/W2949547296","https://openalex.org/W2950577311","https://openalex.org/W2963355447","https://openalex.org/W2963514026","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995","https://openalex.org/W4307474317","https://openalex.org/W2057384730","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2008468404"],"abstract_inverted_index":{"Connected":[0],"high-tech":[1],"systems":[2,32],"allow":[3],"the":[4,18,51,92,134],"gathering":[5],"of":[6,15,29,38,112],"operational":[7],"data":[8],"at":[9],"unprecedented":[10],"volumes.":[11],"A":[12],"direct":[13],"benefit":[14],"this":[16],"is":[17,65,137],"possibility":[19],"to":[20,59,102,141],"extract":[21],"usage":[22,71,142],"models,":[23],"that":[24,133],"is,":[25],"a":[26,55,80,107,110,138],"generic":[27],"representations":[28],"how":[30,54,63],"such":[31],"are":[33,42],"used":[34,61,66],"in":[35,49,67,106],"their":[36],"field":[37],"application.":[39],"Usage":[40],"models":[41],"extremely":[43],"important,":[44],"as":[45,73],"they":[46],"can":[47],"help":[48],"understanding":[50],"discrepancies":[52],"between":[53],"system":[56],"was":[57],"designed":[58],"be":[60],"and":[62,78,104,127],"it":[64],"practice.":[68],"We":[69,114],"interpret":[70],"modelling":[72,95],"an":[74],"unsupervised":[75],"learning":[76],"task":[77],"present":[79],"novel":[81],"algorithm,":[82],"hereafter":[83],"called":[84],"Growing":[85],"Grams":[86],"(GNG),":[87],"which":[88],"relies":[89],"on":[90],"n-grams\u2014arguably":[91],"most":[93],"popular":[94],"technique":[96],"for":[97,124],"natural":[98],"language":[99],"processing":[100,126],"\u2014":[101],"cluster":[103],"model,":[105],"two-step":[108],"rationale,":[109],"dataset":[111],"strings.":[113],"empirically":[115],"compare":[116],"its":[117],"performance":[118],"against":[119],"some":[120],"other":[121],"common":[122],"techniques":[123],"string":[125],"clustering.":[128],"The":[129],"gathered":[130],"results":[131],"suggest":[132],"GNG":[135],"algorithm":[136],"viable":[139],"approach":[140],"modelling.":[143]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}