{"id":"https://openalex.org/W2015319288","doi":"https://doi.org/10.4018/jthi.2006010104","title":"A Method to Quantify Corpus Similarity and its Application to Quantifying the Degree of Literality in a Document","display_name":"A Method to Quantify Corpus Similarity and its Application to Quantifying the Degree of Literality in a Document","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2015319288","doi":"https://doi.org/10.4018/jthi.2006010104","mag":"2015319288"},"language":"en","primary_location":{"id":"doi:10.4018/jthi.2006010104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jthi.2006010104","pdf_url":null,"source":{"id":"https://openalex.org/S130700065","display_name":"International Journal of Technology and Human Interaction","issn_l":"1548-3908","issn":["1548-3908","1548-3916"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Technology and Human Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028024949","display_name":"Etienne Denoual","orcid":null},"institutions":[{"id":"https://openalex.org/I177483745","display_name":"Universit\u00e9 Joseph Fourier","ror":"https://ror.org/02aj0kh94","country_code":"FR","type":"education","lineage":["https://openalex.org/I177483745"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Etienne Denoual","raw_affiliation_strings":["Spoken Language Communication Research Labs, Japan & Joseph Fourier University, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Research Labs, Japan & Joseph Fourier University, France","institution_ids":["https://openalex.org/I177483745"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028024949"],"corresponding_institution_ids":["https://openalex.org/I177483745"],"apc_list":null,"apc_paid":null,"fwci":0.9325,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80461974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":"1","first_page":"51","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.9925000071525574,"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/computer-science","display_name":"Computer science","score":0.8411481380462646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7187544107437134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6111789345741272},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6108094453811646},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5212996006011963},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4669932425022125},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.45018091797828674},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4290284514427185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411481380462646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7187544107437134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6111789345741272},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6108094453811646},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5212996006011963},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4669932425022125},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.45018091797828674},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4290284514427185},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.4018/jthi.2006010104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jthi.2006010104","pdf_url":null,"source":{"id":"https://openalex.org/S130700065","display_name":"International Journal of Technology and Human Interaction","issn_l":"1548-3908","issn":["1548-3908","1548-3916"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Technology and Human Interaction","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.2304","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.2304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.slt.atr.jp/~edenoual/archives/doc_IJTHI2006_ED.pdf","raw_type":"text"},{"id":"pmh:oai:RePEc:igg:jthi00:v:2:y:2006:i:1:p:51-66","is_oa":false,"landing_page_url":"https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/jthi.2006010104","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1784531618","https://openalex.org/W1994851566","https://openalex.org/W2033295622","https://openalex.org/W2093585241","https://openalex.org/W2116780029","https://openalex.org/W2134473597","https://openalex.org/W2138122451"],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2226024386","https://openalex.org/W2250395065","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4376653378","https://openalex.org/W4386247111","https://openalex.org/W2380654781","https://openalex.org/W4327642362"],"abstract_inverted_index":{"Comparing":[0,137],"and":[1,10,118,120,133],"quantifying":[2],"corpora":[3,64,114],"are":[4],"key":[5],"issues":[6],"in":[7,97,115,129,158,175],"corpus-based":[8],"translation":[9],"corpus":[11,40,70],"linguistics,":[12],"for":[13,27],"which":[14,66],"there":[15],"is":[16,93,127],"still":[17],"a":[18,28,39,59,74,179],"notable":[19],"lack":[20],"of":[21,38,52,76,82,90,99,131,152,173,178],"standards.":[22],"This":[23],"makes":[24],"it":[25,138],"difficult":[26],"user":[29],"to":[30,41,94,139,154],"isolate,":[31],"transpose,":[32],"or":[33],"extend":[34],"the":[35,50,80,123,150,171,176],"interesting":[36],"features":[37],"other":[42,140],"NLP":[43],"systems.":[44],"In":[45],"this":[46,91,105,166],"work,":[47],"we":[48,107,168],"address":[49],"issue":[51],"measuring":[53],"similarity":[54,96,125,142],"between":[55,61],"corpora.":[56],"We":[57],"suggest":[58],"scale":[60],"two":[62],"user-chosen":[63],"on":[65,79,111],"any":[67],"third":[68],"given":[69],"can":[71],"be":[72],"assigned":[73],"coefficient":[75,126],"similarity,":[77],"based":[78],"cross-entropy":[81],"statistical":[83],"N-gram":[84],"character":[85],"models.":[86],"A":[87],"possible":[88],"application":[89,153],"framework":[92],"quantify":[95],"terms":[98,130],"literality":[100],"(or,":[101],"conversely,":[102],"orality).":[103],"To":[104],"end,":[106],"carry":[108],"out":[109],"experiments":[110],"several":[112],"well-known":[113],"both":[116],"English":[117],"Japanese":[119],"show":[121],"that":[122],"defined":[124],"robust":[128],"language":[132],"model":[134],"order":[135],"variations.":[136],"existing":[141],"measures":[143],"shows":[144],"similar":[145],"performance":[146],"while":[147],"extending":[148],"widely":[149],"range":[151],"electronic":[155],"data":[156],"written":[157],"languages":[159],"with":[160],"no":[161],"clear":[162],"word":[163],"segmentation.":[164],"Within":[165],"framework,":[167],"further":[169],"investigate":[170],"notion":[172],"homogeneity":[174],"case":[177],"large":[180],"multilingual":[181],"resource.":[182]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}