{"id":"https://openalex.org/W3023958260","doi":"https://doi.org/10.3390/info11050241","title":"Corpus-Based Paraphrase Detection Experiments and Review","display_name":"Corpus-Based Paraphrase Detection Experiments and Review","publication_year":2020,"publication_date":"2020-04-29","ids":{"openalex":"https://openalex.org/W3023958260","doi":"https://doi.org/10.3390/info11050241","mag":"3023958260"},"language":"en","primary_location":{"id":"doi:10.3390/info11050241","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info11050241","pdf_url":"https://www.mdpi.com/2078-2489/11/5/241/pdf?version=1589525338","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/11/5/241/pdf?version=1589525338","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tedo Vrbanec","orcid":"https://orcid.org/0000-0002-4934-255X"},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Tedo Vrbanec","raw_affiliation_strings":["Faculty of Teacher Education, University of Zagreb, Savska Cesta 77, 10000 Zagreb, Croatia"],"raw_orcid":"https://orcid.org/0000-0002-4934-255X","affiliations":[{"raw_affiliation_string":"Faculty of Teacher Education, University of Zagreb, Savska Cesta 77, 10000 Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ana Me\u0161trovi\u0107","orcid":"https://orcid.org/0000-0001-9513-9467"},"institutions":[{"id":"https://openalex.org/I154347574","display_name":"University of Rijeka","ror":"https://ror.org/05r8dqr10","country_code":"HR","type":"education","lineage":["https://openalex.org/I154347574"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Ana Me\u0161trovi\u0107","raw_affiliation_strings":["Center for Artificial Intelligence and Cybersecurity, University of Rijeka, Radmile Matej\u010di\u0107 2, 51000 Rijeka, Croatia","Department of Informatics, University of Rijeka, Radmile Matej\u010di\u0107 2, 51000 Rijeka, Croatia"],"raw_orcid":"https://orcid.org/0000-0001-9513-9467","affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence and Cybersecurity, University of Rijeka, Radmile Matej\u010di\u0107 2, 51000 Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]},{"raw_affiliation_string":"Department of Informatics, University of Rijeka, Radmile Matej\u010di\u0107 2, 51000 Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":1.9841,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.88988105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":"5","first_page":"241","last_page":"241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6358000040054321,"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":0.6358000040054321,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.062300000339746475,"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":0.05310000106692314,"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":0.9889000058174133},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.536300003528595},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4417000114917755},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.4099999964237213}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9889000058174133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7387999892234802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7324000000953674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995999813079834},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38260000944137573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/info11050241","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info11050241","pdf_url":"https://www.mdpi.com/2078-2489/11/5/241/pdf?version=1589525338","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2106.00145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.00145","pdf_url":"https://arxiv.org/pdf/2106.00145","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:doaj.org/article:d533f267911c491fa432c65d3e435272","is_oa":true,"landing_page_url":"https://doaj.org/article/d533f267911c491fa432c65d3e435272","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":"Information, Vol 11, Iss 5, p 241 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/11/5/241/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info11050241","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":"Information; Volume 11; Issue 5; Pages: 241","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info11050241","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info11050241","pdf_url":"https://www.mdpi.com/2078-2489/11/5/241/pdf?version=1589525338","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"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":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023958260.pdf","grobid_xml":"https://content.openalex.org/works/W3023958260.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W95056951","https://openalex.org/W790225446","https://openalex.org/W1493309689","https://openalex.org/W1495179974","https://openalex.org/W1566018662","https://openalex.org/W1662133657","https://openalex.org/W1832693441","https://openalex.org/W1942015218","https://openalex.org/W1967925097","https://openalex.org/W1978394996","https://openalex.org/W1980776243","https://openalex.org/W1990524510","https://openalex.org/W2008127487","https://openalex.org/W2034714661","https://openalex.org/W2078990125","https://openalex.org/W2091432990","https://openalex.org/W2103305545","https://openalex.org/W2108701407","https://openalex.org/W2117130368","https://openalex.org/W2126649078","https://openalex.org/W2131744502","https://openalex.org/W2158997610","https://openalex.org/W2160971205","https://openalex.org/W2161443453","https://openalex.org/W2163922914","https://openalex.org/W2165612380","https://openalex.org/W2250539671","https://openalex.org/W2251427843","https://openalex.org/W2251642297","https://openalex.org/W2293185259","https://openalex.org/W2294860948","https://openalex.org/W2493916176","https://openalex.org/W2572663846","https://openalex.org/W2769280657","https://openalex.org/W2773143256","https://openalex.org/W2887951915","https://openalex.org/W2889769646","https://openalex.org/W2891177506","https://openalex.org/W2921025868","https://openalex.org/W2949927254","https://openalex.org/W2950813464","https://openalex.org/W2953497520","https://openalex.org/W2962739339","https://openalex.org/W2962953307","https://openalex.org/W2963044711","https://openalex.org/W2963196945","https://openalex.org/W2963626623","https://openalex.org/W2963991017","https://openalex.org/W3008252599","https://openalex.org/W3044021949","https://openalex.org/W4237360694","https://openalex.org/W6721511812","https://openalex.org/W6724040256","https://openalex.org/W6730367295","https://openalex.org/W6862954841"],"related_works":[],"abstract_inverted_index":{"Paraphrase":[0,73,81],"detection":[1,114],"is":[2],"important":[3],"for":[4,97],"a":[5,28,85],"number":[6,87],"of":[7,31,34,45,52,88,120],"applications,":[8],"including":[9],"plagiarism":[10],"detection,":[11],"authorship":[12],"attribution,":[13],"question":[14],"answering,":[15],"text":[16,18,98],"summarization,":[17],"mining":[19],"in":[20],"general,":[21],"etc.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,90],"give":[27],"performance":[29],"overview":[30],"various":[32],"types":[33],"corpus-based":[35],"models,":[36,41],"especially":[37],"deep":[38,126],"learning":[39,127],"(DL)":[40],"with":[42,136],"the":[43,50,93],"task":[44],"paraphrase":[46],"detection.":[47],"We":[48],"report":[49],"results":[51],"eight":[53],"models":[54,128,132],"(LSI,":[55],"TF-IDF,":[56],"Word2Vec,":[57],"Doc2Vec,":[58],"GloVe,":[59],"FastText,":[60],"ELMO,":[61],"and":[62,76,78,111,118,140],"USE)":[63],"evaluated":[64],"on":[65,92],"three":[66],"different":[67],"public":[68],"available":[69],"corpora:":[70],"Microsoft":[71],"Research":[72],"Corpus,":[74],"Clough":[75],"Stevenson":[77],"Webis":[79],"Crowd":[80],"Corpus":[82],"2011.":[83],"Through":[84],"great":[86],"experiments,":[89],"decided":[91],"most":[94],"appropriate":[95],"approaches":[96,139],"pre-processing:":[99],"hyper-parameters,":[100],"sub-model":[101],"selection\u2014where":[102],"they":[103],"exist":[104],"(e.g.,":[105],"Skipgram":[106],"vs.":[107],"CBOW),":[108],"distance":[109],"measures,":[110],"semantic":[112],"similarity/paraphrase":[113],"threshold.":[115],"Our":[116],"findings":[117],"those":[119],"other":[121],"researchers":[122],"who":[123],"have":[124,141],"used":[125],"show":[129],"that":[130,143],"DL":[131],"are":[133],"very":[134],"competitive":[135],"traditional":[137],"state-of-the-art":[138],"potential":[142],"should":[144],"be":[145],"further":[146],"developed.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2020-05-13T00:00:00"}
