{"id":"https://openalex.org/W2065635299","doi":"https://doi.org/10.1145/1871840.1871845","title":"Extracting person names from diverse and noisy OCR text","display_name":"Extracting person names from diverse and noisy OCR text","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2065635299","doi":"https://doi.org/10.1145/1871840.1871845","mag":"2065635299"},"language":"en","primary_location":{"id":"doi:10.1145/1871840.1871845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012271845","display_name":"Thomas Packer","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas L. Packer","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014797089","display_name":"Joshua F. Lutes","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua F. Lutes","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073905902","display_name":"Aaron P. Stewart","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron P. Stewart","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084356365","display_name":"David W. Embley","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David W. Embley","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090791372","display_name":"Eric K. Ringger","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric K. Ringger","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029074659","display_name":"Kevin Seppi","orcid":"https://orcid.org/0000-0002-4932-2700"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin D. Seppi","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051602515","display_name":"Lee S. Jensen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee S. Jensen","raw_affiliation_strings":["Ancestry.com, Inc., Provo, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ancestry.com, Inc., Provo, UT, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216784954071045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.643438458442688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5459935665130615},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5091771483421326},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4919874370098114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3463456630706787},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13248416781425476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216784954071045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.643438458442688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5459935665130615},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5091771483421326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4919874370098114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3463456630706787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13248416781425476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1871840.1871845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.211.4082","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.211.4082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.deg.byu.edu/papers/Ancestry_NAACL_HLT_Paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W62486723","https://openalex.org/W1524281572","https://openalex.org/W1780228234","https://openalex.org/W1843650355","https://openalex.org/W1972016971","https://openalex.org/W1972407269","https://openalex.org/W1974123979","https://openalex.org/W2004763266","https://openalex.org/W2011084371","https://openalex.org/W2020278455","https://openalex.org/W2067416210","https://openalex.org/W2075635421","https://openalex.org/W2093370758","https://openalex.org/W2096630656","https://openalex.org/W2099370490","https://openalex.org/W2144578941","https://openalex.org/W2148398225","https://openalex.org/W2150870317"],"related_works":["https://openalex.org/W2357241418","https://openalex.org/W2789919619","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2293457016","https://openalex.org/W3022131925","https://openalex.org/W3169305685","https://openalex.org/W2792377126","https://openalex.org/W2349174110"],"abstract_inverted_index":{"Named":[0],"entity":[1,15],"recognition":[2,16],"from":[3,17,24,125],"scanned":[4],"and":[5,35,59,76,112,118,128],"OCRed":[6,126],"historical":[7,12,18],"documents":[8,19],"can":[9],"contribute":[10],"to":[11,47,72],"research.":[13],"However,":[14],"is":[20],"more":[21],"difficult":[22],"than":[23],"natively":[25],"digital":[26],"data":[27,53,75,127],"because":[28],"of":[29,32,38,50,82,88],"the":[30,36,56,67,79,83,94,101,116],"presence":[31],"word":[33],"errors":[34],"absence":[37],"complete":[39],"formatting":[40],"information.":[41],"We":[42,65,91,114],"apply":[43],"four":[44],"extraction":[45,68,80],"algorithms":[46],"various":[48],"types":[49],"noisy":[51],"OCR":[52],"found":[54],"\u201cin":[55],"wild":[57],"\u201d":[58],"focus":[60],"on":[61],"full":[62],"name":[63],"extraction.":[64,90],"evaluate":[66,93],"quality":[69],"with":[70,96],"respect":[71],"handlabeled":[73],"test":[74],"improve":[77],"upon":[78],"performance":[81],"individual":[84],"systems":[85],"by":[86],"means":[87],"ensemble":[89],"also":[92],"strategies":[95],"different":[97],"applications":[98,103],"in":[99],"mind:":[100],"target":[102],"(browsing":[104],"versus":[105],"retrieval)":[106],"involve":[107],"a":[108],"trade-off":[109],"between":[110],"precision":[111],"recall.":[113],"illustrate":[115],"challenges":[117],"opportunities":[119],"at":[120],"hand":[121],"for":[122,131],"extracting":[123],"names":[124],"identify":[129],"directions":[130],"further":[132],"improvement.":[133],"1":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}