{"id":"https://openalex.org/W2252269695","doi":"https://doi.org/10.3115/v1/p14-2020","title":"Improved Typesetting Models for Historical OCR","display_name":"Improved Typesetting Models for Historical OCR","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2252269695","doi":"https://doi.org/10.3115/v1/p14-2020","mag":"2252269695"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2020","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/p14-2020","pdf_url":"https://doi.org/10.3115/v1/p14-2020","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/p14-2020","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Klein","raw_affiliation_strings":["University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017455302"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.9656,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93353806,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.8416974544525146},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6325734853744507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5670539140701294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5527370572090149},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.528644859790802},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5223991870880127},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.49910521507263184},{"id":"https://openalex.org/keywords/typeface","display_name":"Typeface","score":0.47009560465812683},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45735374093055725},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.41113096475601196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4026884436607361},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16600176692008972},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10354259610176086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416974544525146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6325734853744507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5670539140701294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5527370572090149},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.528644859790802},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5223991870880127},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.49910521507263184},{"id":"https://openalex.org/C80797182","wikidata":"https://www.wikidata.org/wiki/Q17451","display_name":"Typeface","level":2,"score":0.47009560465812683},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45735374093055725},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.41113096475601196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4026884436607361},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16600176692008972},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10354259610176086},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/p14-2020","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/p14-2020","pdf_url":"https://doi.org/10.3115/v1/p14-2020","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.469.5305","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.469.5305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.cs.berkeley.edu/pubs/BergKirkpatrick-Klein_2014_ImprovedOCR_paper.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2020","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/p14-2020","pdf_url":"https://doi.org/10.3115/v1/p14-2020","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252269695.pdf","grobid_xml":"https://content.openalex.org/works/W2252269695.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1495007976","https://openalex.org/W1498238796","https://openalex.org/W1934041838","https://openalex.org/W2001642682","https://openalex.org/W2064218608","https://openalex.org/W2068971329","https://openalex.org/W2133485975","https://openalex.org/W2158522418"],"related_works":["https://openalex.org/W2486962493","https://openalex.org/W2385728895","https://openalex.org/W2071402150","https://openalex.org/W4293093933","https://openalex.org/W3163268046","https://openalex.org/W2053735135","https://openalex.org/W2990826939","https://openalex.org/W2767847244","https://openalex.org/W4280558518","https://openalex.org/W168676510"],"abstract_inverted_index":{"We":[0],"present":[1,68],"richer":[2],"typesetting":[3],"models":[4],"that":[5,73],"extend":[6],"the":[7,22,79],"unsupervised":[8],"historical":[9,107],"document":[10],"recognition":[11],"system":[12],"of":[13,28,60,96,106],"Berg-Kirkpatrick":[14,83],"et":[15,84],"al.":[16,85],"(2013).":[17,86],"The":[18,39],"first":[19],"model":[20,41],"breaks":[21],"independence":[23],"assump-tion":[24],"between":[25],"vertical":[26],"offsets":[27],"neighbor-ing":[29],"glyphs":[30],"and,":[31,47],"in":[32],"experiments,":[33],"substan-tially":[34],"decreases":[35],"transcription":[36],"error":[37,94],"rates.":[38],"second":[40],"simultaneously":[42],"learns":[43],"multiple":[44],"font":[45],"styles":[46],"as":[48],"a":[49,69,91,104],"result,":[50],"is":[51,74],"able":[52],"to":[53,100],"accurately":[54],"track":[55],"italic":[56],"and":[57],"non-italic":[58],"portions":[59],"documents.":[61],"Richer":[62],"mod-els":[63],"complicate":[64],"inference":[65],"so":[66],"we":[67],"new,":[70],"streamlined":[71],"procedure":[72],"over":[75],"25x":[76],"faster":[77],"than":[78],"method":[80],"used":[81],"by":[82],"Our":[87],"final":[88],"sys-tem":[89],"achieves":[90],"relative":[92],"word":[93],"reduc-tion":[95],"22":[97],"%":[98],"compared":[99],"state-of-the-art":[101],"results":[102],"on":[103],"dataset":[105],"newspa-pers.":[108],"1":[109]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}