{"id":"https://openalex.org/W4414206753","doi":"https://doi.org/10.3390/computers14090385","title":"Transformer Models for Paraphrase Detection: A Comprehensive Semantic Similarity Study","display_name":"Transformer Models for Paraphrase Detection: A Comprehensive Semantic Similarity Study","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W4414206753","doi":"https://doi.org/10.3390/computers14090385"},"language":"en","primary_location":{"id":"doi:10.3390/computers14090385","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14090385","pdf_url":"https://www.mdpi.com/2073-431X/14/9/385/pdf?version=1757991041","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"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":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/14/9/385/pdf?version=1757991041","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119623180","display_name":"Dianeliz Ortiz Martes","orcid":null},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dianeliz Ortiz Martes","raw_affiliation_strings":["Department of Mathematics and Systems Engineering, Florida Institute of Technology, Melbourne, FL 32901, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Systems Engineering, Florida Institute of Technology, Melbourne, FL 32901, USA","institution_ids":["https://openalex.org/I106959904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119623181","display_name":"Evan Gunderson","orcid":null},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan Gunderson","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Florida Institute of Technology, Melbourne, FL 32901, USA"],"raw_orcid":"https://orcid.org/0009-0009-1408-2565","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Florida Institute of Technology, Melbourne, FL 32901, USA","institution_ids":["https://openalex.org/I106959904"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Caitlin Neuman","orcid":"https://orcid.org/0009-0003-8134-9692"},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caitlin Neuman","raw_affiliation_strings":["Department of Ocean Engineering and Marine Sciences, Florida Institute of Technology, Melbourne, FL 32901, USA"],"raw_orcid":"https://orcid.org/0009-0003-8134-9692","affiliations":[{"raw_affiliation_string":"Department of Ocean Engineering and Marine Sciences, Florida Institute of Technology, Melbourne, FL 32901, USA","institution_ids":["https://openalex.org/I106959904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073288182","display_name":"Nezamoddin N. Kachouie","orcid":"https://orcid.org/0000-0001-9397-1807"},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nezamoddin N. Kachouie","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Florida Institute of Technology, Melbourne, FL 32901, USA","Department of Mathematics and Systems Engineering, Florida Institute of Technology, Melbourne, FL 32901, USA"],"raw_orcid":"https://orcid.org/0000-0001-9397-1807","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Florida Institute of Technology, Melbourne, FL 32901, USA","institution_ids":["https://openalex.org/I106959904"]},{"raw_affiliation_string":"Department of Mathematics and Systems Engineering, Florida Institute of Technology, Melbourne, FL 32901, USA","institution_ids":["https://openalex.org/I106959904"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073288182"],"corresponding_institution_ids":["https://openalex.org/I106959904"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":6.3497,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9625253,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"14","issue":"9","first_page":"385","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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":0.9940999746322632,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9922000169754028,"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":0.989300012588501,"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/paraphrase","display_name":"Paraphrase","score":0.965399980545044},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.7171000242233276},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6115000247955322},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5863000154495239},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5837000012397766},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4090000092983246},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.38440001010894775}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.965399980545044},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.7171000242233276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6721000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6585000157356262},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6115000247955322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6055999994277954},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4090000092983246},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2773999869823456},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26269999146461487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers14090385","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14090385","pdf_url":"https://www.mdpi.com/2073-431X/14/9/385/pdf?version=1757991041","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"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":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:07b42863f3ea496cb3572f121c7543cc","is_oa":true,"landing_page_url":"https://doaj.org/article/07b42863f3ea496cb3572f121c7543cc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 14, Iss 9, p 385 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers14090385","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14090385","pdf_url":"https://www.mdpi.com/2073-431X/14/9/385/pdf?version=1757991041","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"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":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414206753.pdf","grobid_xml":"https://content.openalex.org/works/W4414206753.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2026593185","https://openalex.org/W2117897510","https://openalex.org/W2970641574","https://openalex.org/W3023958260","https://openalex.org/W3106889297","https://openalex.org/W4310676331","https://openalex.org/W4378652731","https://openalex.org/W4381852095","https://openalex.org/W4394772667","https://openalex.org/W4406905466","https://openalex.org/W4409076718","https://openalex.org/W4410043023","https://openalex.org/W4411619918","https://openalex.org/W4413096359"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"similarity,":[1,68],"the":[2,10,27,42,56,94,125,150,164],"task":[3],"of":[4,30,44,113,127,152,166,168],"determining":[5],"whether":[6],"two":[7],"sentences":[8],"convey":[9],"same":[11],"meaning,":[12],"is":[13,38],"central":[14],"to":[15,124,139],"applications":[16],"such":[17],"as":[18],"paraphrase":[19,159],"detection,":[20],"semantic":[21,183],"search,":[22],"and":[23,47,52,73,83,101,116,172],"question":[24],"answering.":[25],"Despite":[26],"widespread":[28],"adoption":[29],"transformer-based":[31],"models":[32],"for":[33,79,90,158,180],"this":[34],"task,":[35],"their":[36],"performance":[37],"influenced":[39],"by":[40],"both":[41,169],"choice":[43,126],"similarity":[45,108,137,184],"measure":[46],"BERT":[48,115,131],"(bert-base-nli-mean-tokens),":[49],"RoBERTa":[50,117],"(all-roberta-large-v1),":[51],"MPNet":[53],"(all-mpnet-base-v2)":[54],"on":[55],"Microsoft":[57],"Research":[58],"Paraphrase":[59],"Corpus":[60],"(MRPC).":[61],"Sentence":[62],"embeddings":[63],"were":[64],"compared":[65,138],"using":[66,135],"cosine":[67,107,136],"dot":[69],"product,":[70],"Manhattan":[71,140],"distance,":[72,75],"Euclidean":[74,142],"with":[76,106,130],"thresholds":[77,145,173],"optimized":[78,111],"accuracy,":[80,82],"balanced":[81,98],"F1-score.":[84],"Results":[85],"indicate":[86],"a":[87,154],"consistent":[88],"advantage":[89],"MPNet,":[91],"which":[92],"achieved":[93],"highest":[95],"accuracy":[96,99],"(75.6%),":[97],"(71.0%),":[100],"F1-score":[102],"(0.836)":[103],"when":[104,134],"paired":[105],"at":[109],"an":[110],"threshold":[112],"0.671.":[114],"performed":[118],"competitively":[119],"but":[120],"exhibited":[121],"greater":[122],"sensitivity":[123],"Similarity":[128,170],"metric,":[129],"notably":[132],"underperforming":[133],"or":[141],"distance.":[143],"Optimal":[144],"varied":[146],"widely":[147],"(0.334\u20130.867),":[148],"underscoring":[149],"difficulty":[151],"establishing":[153],"single,":[155],"generalizable":[156],"cut-off":[157],"classification.":[160],"These":[161],"findings":[162],"highlight":[163],"value":[165],"fine-tuning":[167],"metrics":[171],"alongside":[174],"model":[175],"selection,":[176],"offering":[177],"practical":[178],"guidance":[179],"designing":[181],"high-accuracy":[182],"systems":[185],"in":[186],"real-world":[187],"NLP":[188],"applications.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}