{"id":"https://openalex.org/W2883184847","doi":"https://doi.org/10.1109/access.2018.2856865","title":"Practical Text Phylogeny for Real-World Settings","display_name":"Practical Text Phylogeny for Real-World Settings","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2883184847","doi":"https://doi.org/10.1109/access.2018.2856865","mag":"2883184847"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2856865","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2856865","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2018.2856865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102911920","display_name":"Bingyu Shen","orcid":"https://orcid.org/0000-0002-0792-7904"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingyu Shen","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-0792-7904","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089679677","display_name":"Christopher W. Forstall","orcid":"https://orcid.org/0000-0001-8004-2603"},"institutions":[{"id":"https://openalex.org/I163902620","display_name":"Mount Allison University","ror":"https://ror.org/03grc6f14","country_code":"CA","type":"education","lineage":["https://openalex.org/I163902620"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christopher W. Forstall","raw_affiliation_strings":["Department of Classics, Mount Allison University, Sackville, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Classics, Mount Allison University, Sackville, Canada","institution_ids":["https://openalex.org/I163902620"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043147904","display_name":"Anderson Rocha","orcid":"https://orcid.org/0000-0002-4236-8212"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Anderson De Rezende Rocha","raw_affiliation_strings":["Institute of Computing, University of Campinas, Campinas, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing, University of Campinas, Campinas, Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091513740","display_name":"Walter J. Scheirer","orcid":"https://orcid.org/0000-0001-9649-8074"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walter J. Scheirer","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1827,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84342511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"41002","last_page":"41012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.9959999918937683,"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/phylogenetics","display_name":"Phylogenetics","score":0.6473474502563477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6307530999183655},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40733039379119873},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.183109849691391},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0833565890789032}],"concepts":[{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.6473474502563477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6307530999183655},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40733039379119873},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.183109849691391},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0833565890789032},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2018.2856865","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2856865","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a86d24e7a9314693b87aca97a60a21b0","is_oa":true,"landing_page_url":"https://doaj.org/article/a86d24e7a9314693b87aca97a60a21b0","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":"IEEE Access, Vol 6, Pp 41002-41012 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2856865","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2856865","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8899999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W185445000","https://openalex.org/W658020064","https://openalex.org/W831781602","https://openalex.org/W1574901103","https://openalex.org/W1591069205","https://openalex.org/W1614298861","https://openalex.org/W1967163043","https://openalex.org/W1983704604","https://openalex.org/W2003959894","https://openalex.org/W2028742638","https://openalex.org/W2045929671","https://openalex.org/W2131744502","https://openalex.org/W2137215532","https://openalex.org/W2148752429","https://openalex.org/W2159800652","https://openalex.org/W2250539671","https://openalex.org/W2250965361","https://openalex.org/W2402166941","https://openalex.org/W2462891382","https://openalex.org/W2508865106","https://openalex.org/W2546055631","https://openalex.org/W2565432423","https://openalex.org/W2620986067","https://openalex.org/W2734330123","https://openalex.org/W2784401422","https://openalex.org/W2950577311","https://openalex.org/W2963219740","https://openalex.org/W2963627878","https://openalex.org/W2998704965","https://openalex.org/W3023279601","https://openalex.org/W3120740533","https://openalex.org/W3123304818","https://openalex.org/W3145128584","https://openalex.org/W4246219036","https://openalex.org/W4285719527","https://openalex.org/W6621906925","https://openalex.org/W6679775712","https://openalex.org/W6680532216","https://openalex.org/W6725015247"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"The":[0],"ease":[1],"with":[2,61,152,171,224],"which":[3],"one":[4,15,43],"can":[5],"edit":[6],"and":[7,45,168,192,232],"redistribute":[8],"digital":[9,39],"documents":[10],"on":[11,41,50,182,211],"the":[12,33,36,42,46,51,53,57,103,142,153,159,180,229],"Internet":[13],"is":[14,64,83,98,124],"of":[16,35,38,48,55,72,144,155,161,207],"modernity's":[17],"great":[18],"achievements,":[19],"but":[20],"it":[21,82,123,170],"also":[22,198],"leads":[23],"to":[24,117,157,202],"some":[25,212],"vexing":[26],"problems.":[27],"With":[28],"growing":[29],"academic":[30],"interest":[31],"in":[32,77,102,132],"study":[34],"evolution":[37],"writing":[40],"hand":[44],"rise":[47],"disinformation":[49],"other,":[52],"problem":[54,80],"identifying":[56],"relationship":[58],"between":[59],"texts":[60,73,92],"similar":[62],"content":[63],"becoming":[65],"more":[66],"important.":[67],"Traditional":[68],"vector":[69],"space":[70],"representations":[71],"have":[74,113],"made":[75],"progress":[76],"solving":[78],"this":[79,138,186],"when":[81],"cast":[84],"as":[85,108,147],"a":[86,94,148,188,203],"reconstruction":[87],"task":[88],"that":[89,219],"organizes":[90],"related":[91],"into":[93],"tree":[95,135],"expressing":[96],"relationships-this":[97],"dubbed":[99],"text":[100,110,120,133,149,175],"phylogeny":[101,134,163],"information":[104],"forensics":[105],"literature.":[106],"However,":[107],"new":[109,204],"representation":[111,150,176],"methods":[112],"been":[114],"successfully":[115],"applied":[116],"many":[118],"other":[119,172,225],"analysis":[121],"problems,":[122],"worth":[125],"investigating":[126],"if":[127],"they":[128],"too":[129],"are":[130,222,233],"used":[131,174],"reconstruction.":[136],"In":[137],"paper,":[139],"we":[140],"explore":[141],"use":[143],"word":[145,220],"embeddings":[146,221],"method,":[151],"aim":[154],"trying":[156],"improve":[158],"accuracy":[160],"reconstructed":[162],"trees":[164],"for":[165,185,228,236],"real-world":[166],"data":[167,190,193,205],"compare":[169],"widely":[173],"methods.":[177],"We":[178,197],"evaluate":[179],"performance":[181],"established":[183],"benchmarks":[184],"task:":[187],"synthetic":[189],"set":[191,206],"collected":[194],"from":[195],"Wikipedia.":[196],"apply":[199],"our":[200],"framework":[201],"fan":[208],"fiction":[209],"based":[210],"famous":[213],"fairy":[214],"tales.":[215],"Experimental":[216],"results":[217],"show":[218],"competitive":[223],"feature":[226],"sets":[227],"published":[230],"benchmarks,":[231],"highly":[234],"effective":[235],"creative":[237],"writing.":[238]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}