{"id":"https://openalex.org/W2404948255","doi":"https://doi.org/10.21437/slate.2007-22","title":"Using natural language parsers in plagiarism detection","display_name":"Using natural language parsers in plagiarism detection","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2404948255","doi":"https://doi.org/10.21437/slate.2007-22","mag":"2404948255"},"language":"en","primary_location":{"id":"doi:10.21437/slate.2007-22","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2007-22","pdf_url":"https://www.isca-archive.org/slate_2007/mozgovoy07_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2007)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/slate_2007/mozgovoy07_slate.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091031054","display_name":"Maxim Mozgovoy","orcid":"https://orcid.org/0000-0003-0684-4012"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Maxim Mozgovoy","raw_affiliation_strings":["University of Joensuu Finland","Joensuu"],"affiliations":[{"raw_affiliation_string":"University of Joensuu Finland","institution_ids":[]},{"raw_affiliation_string":"Joensuu","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077109746","display_name":"Tuomo Kakkonen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Kakkonen","raw_affiliation_strings":["University of Joensuu Finland","Joensuu"],"affiliations":[{"raw_affiliation_string":"University of Joensuu Finland","institution_ids":[]},{"raw_affiliation_string":"Joensuu","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036285785","display_name":"Erkki Sutinen","orcid":"https://orcid.org/0000-0002-1020-3325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erkki Sutinen","raw_affiliation_strings":["University of Joensuu Finland","Joensuu"],"affiliations":[{"raw_affiliation_string":"University of Joensuu Finland","institution_ids":[]},{"raw_affiliation_string":"Joensuu","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091031054"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9345,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.8915468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T10028","display_name":"Topic Modeling","score":0.994700014591217,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.8403677940368652},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6636065244674683},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4827117621898651},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.46584948897361755},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46132534742355347},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4189237058162689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4170129597187042},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40838688611984253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403677940368652},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6636065244674683},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4827117621898651},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.46584948897361755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46132534742355347},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4189237058162689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4170129597187042},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40838688611984253},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/slate.2007-22","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2007-22","pdf_url":"https://www.isca-archive.org/slate_2007/mozgovoy07_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2007)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.144.320","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/mozgovoy/homepage/papers/MKS07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.385.1324","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.1324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isca-speech.org/archive_open/archive_papers/slate_2007/sle7_077.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.463.6137","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.463.6137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~max/mainpage_files/files/SLaTE07_Mozgovoy_Plagiarism_Detection.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.21437/slate.2007-22","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2007-22","pdf_url":"https://www.isca-archive.org/slate_2007/mozgovoy07_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2007)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2404948255.pdf","grobid_xml":"https://content.openalex.org/works/W2404948255.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W58323294","https://openalex.org/W1508977358","https://openalex.org/W1632114991","https://openalex.org/W1797297385","https://openalex.org/W1970961429","https://openalex.org/W2024438214","https://openalex.org/W2066688923","https://openalex.org/W2073265902","https://openalex.org/W2097606805","https://openalex.org/W2116735155","https://openalex.org/W2148484595","https://openalex.org/W2152907450","https://openalex.org/W2163840964","https://openalex.org/W2343954916","https://openalex.org/W6638232714","https://openalex.org/W6674783156","https://openalex.org/W6677278745","https://openalex.org/W6682510499","https://openalex.org/W6683967697"],"related_works":["https://openalex.org/W4287126803","https://openalex.org/W3168266056","https://openalex.org/W4250737080","https://openalex.org/W2112890327","https://openalex.org/W2735162248","https://openalex.org/W311440260","https://openalex.org/W2945111072","https://openalex.org/W1496191935","https://openalex.org/W2293063786","https://openalex.org/W2911292476"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,10,13,39,54],"plagiarism":[3,55,78],"detection":[4],"system":[5],"design":[6],"is":[7,48],"a":[8,67],"subject":[9],"numerous":[11],"works":[12],"the":[14,40,52],"last":[15],"decades.":[16],"Various":[17],"advanced":[18],"file-file":[19],"comparison":[20],"techniques":[21],"were":[22],"developed.":[23],"However,":[24],"most":[25],"existing":[26],"systems,":[27],"aimed":[28],"at":[29],"natural":[30,68],"language":[31,69],"texts,":[32],"do":[33],"not":[34],"perform":[35],"any":[36],"significant":[37],"preprocessing":[38],"input":[41],"documents.":[42],"So":[43],"in":[44],"many":[45],"cases":[46],"it":[47],"possible":[49],"to":[50,74],"hide":[51],"presence":[53],"by":[56],"utilizing":[57],"some":[58],"simple":[59],"techniques.":[60],"In":[61],"this":[62],"work":[63],"we":[64],"show":[65],"how":[66],"parser":[70],"can":[71],"be":[72],"used":[73],"fight":[75],"against":[76],"basic":[77],"hiding":[79],"methods.":[80]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
