{"id":"https://openalex.org/W2611197953","doi":"https://doi.org/10.18653/v1/p17-2065","title":"Automatic Compositor Attribution in the First Folio of Shakespeare","display_name":"Automatic Compositor Attribution in the First Folio of Shakespeare","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2611197953","doi":"https://doi.org/10.18653/v1/p17-2065","mag":"2611197953"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-2065","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2065","pdf_url":"https://www.aclweb.org/anthology/P17-2065.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-2065.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004582255","display_name":"Maria Ryskina","orcid":"https://orcid.org/0009-0002-5936-1380"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maria Ryskina","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014908997","display_name":"Hannah Alpert-Abrams","orcid":"https://orcid.org/0000-0002-1019-9223"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannah Alpert-Abrams","raw_affiliation_strings":["Comparative Literature Program, University of Texas at Austin,","The University of Texas at Austin, Austin, United States"],"affiliations":[{"raw_affiliation_string":"Comparative Literature Program, University of Texas at Austin,","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087636608","display_name":"Dan Garrette","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Garrette","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004582255"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.03804296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11309","display_name":"Music and Audio Processing","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/folio","display_name":"Folio","score":0.9459909200668335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7188141345977783},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6325262188911438},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.6256694793701172},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.598989725112915},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5399788022041321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5038058161735535},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49385887384414673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49348580837249756},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.45874011516571045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4451358914375305},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.15421569347381592},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12489274144172668},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.09188541769981384},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06736040115356445}],"concepts":[{"id":"https://openalex.org/C2779520441","wikidata":"https://www.wikidata.org/wiki/Q772267","display_name":"Folio","level":2,"score":0.9459909200668335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188141345977783},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6325262188911438},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.6256694793701172},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.598989725112915},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5399788022041321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5038058161735535},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49385887384414673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49348580837249756},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.45874011516571045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4451358914375305},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.15421569347381592},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12489274144172668},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.09188541769981384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06736040115356445},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p17-2065","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2065","pdf_url":"https://www.aclweb.org/anthology/P17-2065.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.07875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.07875","pdf_url":"https://arxiv.org/pdf/1704.07875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:2611197953","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1704.07875.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1704.07875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.07875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-2065","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2065","pdf_url":"https://www.aclweb.org/anthology/P17-2065.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4656502445","display_name":"RI: Small: Collaborative Research: Unsupervised Transcription of Early Modern Documents","funder_award_id":"1618044","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2611197953.pdf","grobid_xml":"https://content.openalex.org/works/W2611197953.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1981745473"],"related_works":["https://openalex.org/W2962707762","https://openalex.org/W1602390003","https://openalex.org/W2906214563","https://openalex.org/W2110361663","https://openalex.org/W979517894","https://openalex.org/W2795779899","https://openalex.org/W2811140637","https://openalex.org/W1579452529","https://openalex.org/W161867551","https://openalex.org/W2167929403","https://openalex.org/W2948334485","https://openalex.org/W2101793424","https://openalex.org/W1988167922","https://openalex.org/W2081618810","https://openalex.org/W1779595697","https://openalex.org/W47678462","https://openalex.org/W3184069615","https://openalex.org/W2617572518","https://openalex.org/W2000263793","https://openalex.org/W3202367703"],"abstract_inverted_index":{"Compositor":[0],"attribution,":[1],"the":[2,12,16,35,50,73,88],"clustering":[3],"of":[4,26,31,34,62,76,81,90],"pages":[5],"in":[6],"a":[7,19,43],"historical":[8],"printed":[9,36],"document":[10],"by":[11],"individual":[13],"who":[14],"set":[15],"type,":[17],"is":[18,87],"bibliographic":[20],"task":[21],"that":[22,47,70,86],"relies":[23],"on":[24,84],"analysis":[25],"orthographic":[27],"variation":[28],"and":[29,52],"inspection":[30],"visual":[32,53],"details":[33],"page.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"introduce":[42],"novel":[44],"unsupervised":[45],"model":[46,67],"jointly":[48],"describes":[49],"textual":[51],"features":[54],"needed":[55],"to":[56,60],"distinguish":[57],"compositors.":[58],"Applied":[59],"images":[61],"Shakespeare's":[63],"First":[64],"Folio,":[65],"our":[66],"predicts":[68],"attributions":[69],"agree":[71],"with":[72,78],"manual":[74],"judgements":[75],"bibliographers":[77],"an":[79],"accuracy":[80],"87%,":[82],"even":[83],"text":[85],"output":[89],"OCR.":[91]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}