{"id":"https://openalex.org/W2322107118","doi":"https://doi.org/10.1145/2809544.2809547","title":"Cost-Effective Information Extraction from Lists in OCRed Historical Documents","display_name":"Cost-Effective Information Extraction from Lists in OCRed Historical Documents","publication_year":2015,"publication_date":"2015-08-22","ids":{"openalex":"https://openalex.org/W2322107118","doi":"https://doi.org/10.1145/2809544.2809547","mag":"2322107118"},"language":"en","primary_location":{"id":"doi:10.1145/2809544.2809547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2809544.2809547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-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/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":true,"raw_author_name":"Thomas L. Packer","raw_affiliation_strings":["Department of Computer Science, Brigham Young University, Provo, Utah 84602"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brigham Young University, Provo, Utah 84602","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","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":["Department of Computer Science, Brigham Young University, Provo, Utah 84602"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brigham Young University, Provo, Utah 84602","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012271845"],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78359759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T11269","display_name":"Algorithms and Data Compression","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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8456222414970398},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7569175958633423},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6575223207473755},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6087366938591003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5425726175308228},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.46999964118003845},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.44813355803489685},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.44646668434143066},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.4357791244983673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4042922258377075},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38660967350006104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38476991653442383},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.1016710102558136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456222414970398},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7569175958633423},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6575223207473755},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6087366938591003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425726175308228},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.46999964118003845},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.44813355803489685},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.44646668434143066},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.4357791244983673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4042922258377075},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38660967350006104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38476991653442383},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.1016710102558136},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2809544.2809547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2809544.2809547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W196969749","https://openalex.org/W597165831","https://openalex.org/W1553019137","https://openalex.org/W1691409177","https://openalex.org/W2059513841","https://openalex.org/W2080132606","https://openalex.org/W2083330748","https://openalex.org/W2118778987","https://openalex.org/W2131165428","https://openalex.org/W2135767707","https://openalex.org/W2145007893","https://openalex.org/W2154339456","https://openalex.org/W2160338566","https://openalex.org/W2182404622","https://openalex.org/W2914331073","https://openalex.org/W4206723194","https://openalex.org/W4240049929","https://openalex.org/W4250128322","https://openalex.org/W6686198202"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2535098683","https://openalex.org/W2367919820","https://openalex.org/W2437596814","https://openalex.org/W2183954062","https://openalex.org/W167001757","https://openalex.org/W2996274640","https://openalex.org/W156512209","https://openalex.org/W4323520198","https://openalex.org/W3119061519"],"abstract_inverted_index":{"To":[0],"work":[1],"well,":[2],"machine-learning-based":[3],"approaches":[4],"to":[5,32,128,134],"information":[6,71,158],"extraction":[7,72],"and":[8,19,36,90,121,159,163,169,175],"ontology":[9,135],"population":[10],"often":[11],"require":[12],"a":[13,30,39,54,109,140,172,183],"large":[14],"number":[15],"of":[16,38,63,70,82,85,93,148,154,156,179],"manually":[17],"selected":[18],"annotated":[20],"examples.":[21,144],"In":[22],"this":[23],"paper,":[24],"we":[25,104],"propose":[26],"ListReader":[27,166,180],"which":[28],"provides":[29],"way":[31],"train":[33],"the":[34,61,68,130,149],"structure":[35],"parameters":[37],"Hidden":[40],"Markov":[41],"Model":[42],"(HMM)":[43],"without":[44],"requiring":[45],"any":[46],"labeled":[47],"training":[48,102,116],"data.":[49],"The":[50,77,100,115],"induced":[51],"HMM":[52,78,119,151],"is":[53,80,106],"wrapper---a":[55],"function":[56],"that":[57,165,181],"hides":[58],"within":[59],"it":[60],"complexities":[62,69],"low-level":[64],"processing---in":[65],"ListReader's":[66],"case":[67],"from":[73,132,139],"OCRed":[74],"historical":[75],"documents.":[76],"wrapper":[79,120,133],"capable":[81],"recognizing":[83],"lists":[84],"records":[86],"in":[87,152],"text":[88],"documents":[89],"associating":[91],"subsets":[92],"identical":[94],"fields":[95],"across":[96],"related":[97],"record":[98],"templates.":[99],"algorithmic":[101],"method":[103],"employ":[105],"based":[107],"on":[108],"novel":[110],"unsupervised":[111],"active":[112,125],"grammar-induction":[113],"framework.":[114],"produces":[117],"an":[118,123,176],"uses":[122],"efficient":[124],"sampling":[126],"process":[127],"complete":[129],"mapping":[131],"by":[136],"requesting":[137],"annotations":[138],"user":[141],"for":[142],"automatically-selected":[143],"We":[145],"measure":[146],"performance":[147],"final":[150],"terms":[153],"F-measure":[155],"extracted":[157],"manual":[160],"annotation":[161],"cost":[162],"show":[164],"learns":[167],"faster":[168],"better":[170],"than":[171],"state-of-the-art":[173],"baseline":[174],"alternate":[177],"version":[178],"induces":[182],"regular-expression":[184],"wrapper.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}