{"id":"https://openalex.org/W2114097960","doi":"https://doi.org/10.1093/llc/fqt002","title":"Document dissimilarity within and across languages: A benchmarking study","display_name":"Document dissimilarity within and across languages: A benchmarking study","publication_year":2013,"publication_date":"2013-02-06","ids":{"openalex":"https://openalex.org/W2114097960","doi":"https://doi.org/10.1093/llc/fqt002","mag":"2114097960"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqt002","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqt002","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","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/A5110883776","display_name":"Richard S. Forsyth","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"R. S. Forsyth","raw_affiliation_strings":["University of Leeds, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds, UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072701587","display_name":"Serge Sharoff","orcid":"https://orcid.org/0000-0002-4877-0210"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S. Sharoff","raw_affiliation_strings":["University of Leeds, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds, UK","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4469,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9452355,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"29","issue":"1","first_page":"6","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9927999973297119,"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":0.9927999973297119,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8257752656936646},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.5232883095741272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44257980585098267},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43784815073013306},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35050323605537415},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.33565831184387207},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09209907054901123},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.07767796516418457}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8257752656936646},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.5232883095741272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44257980585098267},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43784815073013306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35050323605537415},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.33565831184387207},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09209907054901123},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.07767796516418457},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/llc/fqt002","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqt002","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","raw_type":"journal-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:75761","is_oa":false,"landing_page_url":"http://eprints.whiterose.ac.uk/75761/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W259451172","https://openalex.org/W1497576442","https://openalex.org/W1533010523","https://openalex.org/W1578874851","https://openalex.org/W1937758960","https://openalex.org/W1956559956","https://openalex.org/W1964788111","https://openalex.org/W1966343454","https://openalex.org/W1969001549","https://openalex.org/W1990950330","https://openalex.org/W2007780422","https://openalex.org/W2020861455","https://openalex.org/W2021034890","https://openalex.org/W2028776121","https://openalex.org/W2067432306","https://openalex.org/W2096554363","https://openalex.org/W2106736575","https://openalex.org/W2118606687","https://openalex.org/W2123998733","https://openalex.org/W2133753644","https://openalex.org/W2134312057","https://openalex.org/W2144211451","https://openalex.org/W2153222072","https://openalex.org/W2166122509","https://openalex.org/W2582743722","https://openalex.org/W2912780347","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2000169967"],"abstract_inverted_index":{"Quantifying":[0],"the":[1,53,113,118],"similarity":[2,28,83,97,152],"or":[3],"dissimilarity":[4],"between":[5],"documents":[6],"is":[7,178],"an":[8],"important":[9],"task":[10],"in":[11,74,81,124,128],"authorship":[12],"attribution,":[13],"information":[14],"retrieval,":[15],"plagiarism":[16],"detection,":[17],"text":[18,77],"mining,":[19],"and":[20,33,181],"many":[21],"other":[22],"areas":[23],"of":[24,52,55,60,120,158],"linguistic":[25],"computing.":[26],"Numerous":[27],"indices":[29,45],"have":[30],"been":[31,40,79],"devised":[32],"used,":[34],"but":[35],"relatively":[36],"little":[37],"attention":[38],"has":[39,78],"paid":[41],"to":[42,112,165,173],"calibrating":[43],"such":[44],"against":[46,103],"externally":[47],"imposed":[48],"standards,":[49],"mainly":[50],"because":[51],"difficulty":[54],"establishing":[56],"agreed":[57],"reference":[58,104],"levels":[59,105],"inter-text":[61,171,174],"similarity.":[62],"The":[63],"present":[64],"article":[65],"introduces":[66],"a":[67,82,93,121],"multi-register":[68],"corpus":[69],"gathered":[70],"for":[71,95],"this":[72,167],"purpose,":[73],"which":[75,129],"each":[76],"located":[80],"space":[84],"based":[85],"on":[86,153],"ratings":[87],"by":[88],"human":[89,108],"readers.":[90],"This":[91],"provides":[92],"resource":[94],"testing":[96],"measures":[98,133,142],"derived":[99,106],"from":[100,107,169],"computational":[101],"text-processing":[102],"judgement,":[109],"i.e.":[110],"external":[111],"texts":[114],"themselves.":[115],"We":[116],"describe":[117],"results":[119],"benchmarking":[122],"study":[123],"five":[125],"different":[126],"languages":[127,177],"some":[130],"widely":[131],"used":[132],"perform":[134],"comparatively":[135],"poorly.":[136],"In":[137],"particular,":[138],"several":[139],"alternative":[140],"correlational":[141],"(Pearson":[143],"r,":[144],"Spearman":[145],"rho,":[146],"tetrachoric":[147],"correlation)":[148],"consistently":[149],"outperform":[150],"cosine":[151],"our":[154],"data.":[155],"A":[156],"method":[157,168],"using":[159],"what":[160],"we":[161],"call":[162],"\u2018anchor":[163],"texts\u2019":[164],"extend":[166],"monolingual":[170],"similarity-scoring":[172,175],"across":[176],"also":[179],"proposed":[180],"tested.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}