{"id":"https://openalex.org/W2757390651","doi":"https://doi.org/10.18653/v1/d17-1077","title":"The Labeled Segmentation of Printed Books","display_name":"The Labeled Segmentation of Printed Books","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2757390651","doi":"https://doi.org/10.18653/v1/d17-1077","mag":"2757390651"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1077","pdf_url":"https://www.aclweb.org/anthology/D17-1077.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/D17-1077.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002428796","display_name":"Lara McConnaughey","orcid":null},"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":"Lara McConnaughey","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114029578","display_name":"Jennifer Dai","orcid":null},"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":"Jennifer Dai","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058212934","display_name":"David Bamman","orcid":"https://orcid.org/0009-0003-1171-9408"},"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":"David Bamman","raw_affiliation_strings":["School of Information University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"School of Information University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.424,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":12,"citation_normalized_percentile":{"value":0.704067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":null,"issue":null,"first_page":"737","last_page":"747"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwriting Recognition and Text Detection","score":0.9981,"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":"Handwriting Recognition and Text Detection","score":0.9981,"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/T12377","display_name":"Digital Humanities in Literary Studies","score":0.9972,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Automatic Video Summarization and Analysis","score":0.9963,"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/macro","display_name":"Macro","score":0.6352949},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.61488825},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.598814},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.49206585},{"id":"https://openalex.org/keywords/multimodal-indexing","display_name":"Multimodal Indexing","score":0.489977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698625},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6839976},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6523273},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6512444},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.6352949},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.61488825},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.598814},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5681259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5530192},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.52681947},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.49206585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4881476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36205745},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24929339},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1598194},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.085073024},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1077","pdf_url":"https://www.aclweb.org/anthology/D17-1077.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1077","pdf_url":"https://www.aclweb.org/anthology/D17-1077.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.45}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":39,"referenced_works":["https://openalex.org/W1570098300","https://openalex.org/W1691157804","https://openalex.org/W1828401780","https://openalex.org/W1968290777","https://openalex.org/W1969168960","https://openalex.org/W2002006695","https://openalex.org/W2017776283","https://openalex.org/W2019096529","https://openalex.org/W2027823133","https://openalex.org/W2031837460","https://openalex.org/W2035439590","https://openalex.org/W2047961976","https://openalex.org/W2053050503","https://openalex.org/W2063630165","https://openalex.org/W2095881835","https://openalex.org/W2102343050","https://openalex.org/W2106279089","https://openalex.org/W2107038821","https://openalex.org/W2107550813","https://openalex.org/W2131954182","https://openalex.org/W2133485975","https://openalex.org/W2136783895","https://openalex.org/W2144499799","https://openalex.org/W2147880316","https://openalex.org/W2148763605","https://openalex.org/W2148818577","https://openalex.org/W2149551320","https://openalex.org/W2161315621","https://openalex.org/W2250837944","https://openalex.org/W2252269695","https://openalex.org/W2349666009","https://openalex.org/W2500585446","https://openalex.org/W2741103579","https://openalex.org/W2911964244","https://openalex.org/W2916815186","https://openalex.org/W2962902328","https://openalex.org/W2963780471","https://openalex.org/W4252065207","https://openalex.org/W634710709"],"related_works":["https://openalex.org/W4205247302","https://openalex.org/W2592395359","https://openalex.org/W2535231171","https://openalex.org/W2501551404","https://openalex.org/W2468652214","https://openalex.org/W2326647871","https://openalex.org/W2130144716","https://openalex.org/W2045342254","https://openalex.org/W1504527458","https://openalex.org/W1501331687"],"abstract_inverted_index":{"We":[0,28],"introduce":[1],"the":[2,22,31,54],"task":[3],"of":[4,17,25,56,59,74,81],"book":[5],"structure":[6,24],"labeling:":[7],"segmenting":[8],"and":[9,49,76],"assigning":[10],"a":[11,36,64,77],"fixed":[12],"category":[13],"(such":[14],"as":[15],"Table":[16],"Contents,":[18],"Preface,":[19],"Index)":[20],"to":[21],"document":[23],"printed":[26],"books.":[27],"manually":[29],"annotate":[30],"page-level":[32],"structural":[33],"categories":[34],"for":[35],"large":[37],"dataset":[38],"totaling":[39],"294,816":[40],"pages":[41],"in":[42],"1,055":[43],"books":[44],"evenly":[45],"sampled":[46],"from":[47],"1750-1922,":[48],"present":[50],"empirical":[51],"results":[52],"comparing":[53],"performance":[55],"several":[57],"classes":[58],"models.":[60],"The":[61],"best-performing":[62],"model,":[63],"bidirectional":[65],"LSTM":[66],"with":[67],"rich":[68],"features,":[69],"achieves":[70],"an":[71],"overall":[72],"accuracy":[73],"95.8":[75],"class-balanced":[78],"macro":[79],"F-score":[80],"71.4.":[82]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2757390651","counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2024-11-27T03:54:54.640258","created_date":"2017-10-06"}
