{"id":"https://openalex.org/W4308509801","doi":"https://doi.org/10.3390/computation10110200","title":"Greedy Texts Similarity Mapping","display_name":"Greedy Texts Similarity Mapping","publication_year":2022,"publication_date":"2022-11-08","ids":{"openalex":"https://openalex.org/W4308509801","doi":"https://doi.org/10.3390/computation10110200"},"language":"en","primary_location":{"id":"doi:10.3390/computation10110200","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation10110200","pdf_url":"https://www.mdpi.com/2079-3197/10/11/200/pdf?version=1668675228","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2079-3197/10/11/200/pdf?version=1668675228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005679713","display_name":"Aliya Jangabylova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Aliya Jangabylova","raw_affiliation_strings":["Institute of Information and Computational Technologies, Pushkin Str., 125, Almaty 050010, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Pushkin Str., 125, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053595206","display_name":"Alexander Krassovitskiy","orcid":"https://orcid.org/0000-0003-2948-374X"},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Alexander Krassovitskiy","raw_affiliation_strings":["Institute of Information and Computational Technologies, Pushkin Str., 125, Almaty 050010, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Pushkin Str., 125, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031261567","display_name":"Rustam Mussabayev","orcid":"https://orcid.org/0000-0001-7283-5144"},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Rustam Mussabayev","raw_affiliation_strings":["Institute of Information and Computational Technologies, Pushkin Str., 125, Almaty 050010, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Pushkin Str., 125, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021380909","display_name":"Irina Ualiyeva","orcid":"https://orcid.org/0000-0003-3853-8896"},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Irina Ualiyeva","raw_affiliation_strings":["Faculty of Information Technology, Al-Farabi Kazakh National University, 71 Al-Farabi Ave., Almaty 050040, Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Al-Farabi Kazakh National University, 71 Al-Farabi Ave., Almaty 050040, Kazakhstan","institution_ids":["https://openalex.org/I185571130"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005679713","https://openalex.org/A5021380909","https://openalex.org/A5031261567","https://openalex.org/A5053595206"],"corresponding_institution_ids":["https://openalex.org/I185571130","https://openalex.org/I4210135055"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.1379,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55601727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":"11","first_page":"200","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T13629","display_name":"Text Readability and Simplification","score":0.9976000189781189,"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/similarity","display_name":"Similarity (geometry)","score":0.8146795034408569},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6869412660598755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.682579517364502},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6813624501228333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6591881513595581},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.654169499874115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6527622938156128},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6185689568519592},{"id":"https://openalex.org/keywords/earth-movers-distance","display_name":"Earth mover's distance","score":0.49313682317733765},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.42213353514671326},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32782527804374695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3237949013710022},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22347554564476013},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20835834741592407},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11210548877716064}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8146795034408569},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6869412660598755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682579517364502},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6813624501228333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6591881513595581},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.654169499874115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527622938156128},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6185689568519592},{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.49313682317733765},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.42213353514671326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32782527804374695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3237949013710022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22347554564476013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20835834741592407},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11210548877716064},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/computation10110200","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation10110200","pdf_url":"https://www.mdpi.com/2079-3197/10/11/200/pdf?version=1668675228","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:77694324a7834c718581a2debf3340a2","is_oa":true,"landing_page_url":"https://doaj.org/article/77694324a7834c718581a2debf3340a2","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computation, Vol 10, Iss 11, p 200 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2079-3197/10/11/200/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/computation10110200","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computation; Volume 10; Issue 11; Pages: 200","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/computation10110200","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation10110200","pdf_url":"https://www.mdpi.com/2079-3197/10/11/200/pdf?version=1668675228","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308509801.pdf","grobid_xml":"https://content.openalex.org/works/W4308509801.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1015675232","https://openalex.org/W1529026127","https://openalex.org/W1615991656","https://openalex.org/W1978394996","https://openalex.org/W1980867644","https://openalex.org/W2060772891","https://openalex.org/W2129250947","https://openalex.org/W2136213019","https://openalex.org/W2142995284","https://openalex.org/W2143668817","https://openalex.org/W2148374900","https://openalex.org/W2163380389","https://openalex.org/W2165533158","https://openalex.org/W2250539671","https://openalex.org/W2564590796","https://openalex.org/W2891378076","https://openalex.org/W2896457183","https://openalex.org/W2947771965","https://openalex.org/W2950146322","https://openalex.org/W3081886688","https://openalex.org/W4210907736","https://openalex.org/W4231510805","https://openalex.org/W4283329669","https://openalex.org/W4284882427","https://openalex.org/W4288064845","https://openalex.org/W4297120310","https://openalex.org/W4300388893","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2015573458","https://openalex.org/W2125221595","https://openalex.org/W1540114044","https://openalex.org/W1971648542","https://openalex.org/W2049988766","https://openalex.org/W2516227785","https://openalex.org/W333414154","https://openalex.org/W2132438428","https://openalex.org/W3029667796","https://openalex.org/W4285226496"],"abstract_inverted_index":{"The":[0],"documents":[1],"similarity":[2,31,38,65,69,102,143,161],"metric":[3,66],"is":[4,73,167],"a":[5,60,96,168],"substantial":[6],"tool":[7],"applied":[8,78],"in":[9,15,91,120,154],"areas":[10],"such":[11],"as":[12],"determining":[13],"topic":[14],"relation":[16],"to":[17,24,76,106,132],"documents,":[18],"plagiarism":[19],"detection,":[20],"or":[21,29,134],"problems":[22],"necessary":[23],"capture":[25],"the":[26,37,42,48,64,107,113,121,138],"semantic,":[27],"syntactic,":[28],"structural":[30],"of":[32,36,44,63,142],"texts.":[33,108],"Evaluated":[34],"results":[35],"measure":[39],"depend":[40],"on":[41,95],"types":[43],"word":[45,85,101,115],"represented":[46],"and":[47,51,103,127,158,163,174],"problem":[49,126],"statement":[50],"can":[52],"be":[53,77],"time-consuming.":[54],"In":[55,137],"this":[56],"paper,":[57],"we":[58,148],"present":[59],"problem-independent":[61],"algorithm":[62,119],"greedy":[67],"texts":[68,93],"mapping":[70],"(GTSM),":[71],"which":[72],"computationally":[74],"efficient":[75],"for":[79,171],"large":[80],"datasets":[81],"with":[82,112,145,156],"any":[83],"preferred":[84],"vectorization":[86],"models.":[87],"GTSM":[88,166],"maps":[89],"words":[90],"two":[92],"based":[94],"decision":[97],"rule":[98],"that":[99,129,165],"evaluates":[100],"their":[104],"importance":[105],"We":[109],"compare":[110],"it":[111,130],"well-known":[114],"mover\u2019s":[116,160],"distance":[117],"(WMD)":[118],"k-nearest":[122],"neighbors":[123],"text":[124],"classification":[125],"find":[128],"leads":[131],"similar":[133],"better":[135],"results.":[136],"correlation":[139,152],"evaluation":[140],"task":[141],"measures":[144],"human-judged":[146],"scores,":[147],"demonstrate":[149],"its":[150],"higher":[151],"scores":[153],"comparison":[155],"WMD":[157],"sentence":[159],"(SMS)":[162],"show":[164],"decent":[169],"alternative":[170],"both":[172],"word-level":[173],"sentence-level":[175],"tasks.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2022-11-12T00:00:00"}