{"id":"https://openalex.org/W2023354950","doi":"https://doi.org/10.1145/1871840.1871843","title":"Document","display_name":"Document","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2023354950","doi":"https://doi.org/10.1145/1871840.1871843","mag":"2023354950"},"language":"en","primary_location":{"id":"doi:10.1145/1871840.1871843","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871843","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":"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/A5085566571","display_name":"Herv\u00e9 D\u00e9jean","orcid":"https://orcid.org/0000-0002-9837-5358"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Herv\u00e9 D\u00e9jean","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Research Centre Europe, Meylan, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061308895","display_name":"Jean-Luc Meunier","orcid":null},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Meunier","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Research Centre Europe, Meylan, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France#TAB#","institution_ids":["https://openalex.org/I33976269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085566571"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":null,"apc_paid":null,"fwci":0.9021,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79765297,"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":"3","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.996999979019165,"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/T11269","display_name":"Algorithms and Data Compression","score":0.996999979019165,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9968000054359436,"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":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8066869974136353},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6281037926673889},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6209731698036194},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.5770853161811829},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5614559650421143},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.538374125957489},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5066514611244202},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.5048697590827942},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.45595884323120117},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4350966513156891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37397071719169617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3243938088417053},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.15710440278053284},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.14477521181106567},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1228029727935791},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.11407172679901123},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09735405445098877},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09142142534255981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066869974136353},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6281037926673889},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6209731698036194},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.5770853161811829},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5614559650421143},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.538374125957489},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5066514611244202},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.5048697590827942},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.45595884323120117},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4350966513156891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37397071719169617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3243938088417053},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.15710440278053284},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.14477521181106567},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1228029727935791},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.11407172679901123},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09735405445098877},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09142142534255981},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871840.1871843","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871840.1871843","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320333065","display_name":"Seventh Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W10112829","https://openalex.org/W1972697075","https://openalex.org/W1999067635","https://openalex.org/W2021795960","https://openalex.org/W2024871791","https://openalex.org/W2035439590","https://openalex.org/W2040799618","https://openalex.org/W2100772677","https://openalex.org/W2107038821","https://openalex.org/W2109044256","https://openalex.org/W2116604999","https://openalex.org/W2133058591","https://openalex.org/W2163529831","https://openalex.org/W2406727294","https://openalex.org/W4315746690"],"related_works":["https://openalex.org/W1971234693","https://openalex.org/W182542749","https://openalex.org/W2268591602","https://openalex.org/W2573990671","https://openalex.org/W2000372441","https://openalex.org/W2178966353","https://openalex.org/W1502347913","https://openalex.org/W3150102101","https://openalex.org/W4377821420","https://openalex.org/W2610978234"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"will":[4],"present":[5],"a":[6,25,38,48,74],"set":[7],"of":[8,14,80,89,115],"experiments":[9],"using":[10],"large":[11],"digitalized":[12],"collections":[13],"books":[15],"to":[16,93],"show":[17],"that":[18],"logical":[19,43],"structures":[20],"can":[21],"be":[22],"extracted":[23],"with":[24],"good":[26],"quality":[27],"when":[28],"working":[29],"at":[30,71],"document":[31,72,81,117],"level.":[32],"The":[33],"proposed":[34],"solution":[35],"relies":[36],"on":[37],"twofold":[39],"method:":[40],"first":[41],"specific":[42],"elements":[44,56,126],"are":[45,57,91],"recognized":[46,55],"by":[47,59,104,112,128],"given":[49],"method.":[50],"Then":[51],"models":[52,85],"for":[53],"the":[54,113],"generated":[58],"combining":[60,86],"layout,":[61],"content":[62],"and":[63,100,121],"labeling":[64,101],"information.":[65],"Model":[66],"inference":[67],"is":[68,110],"made":[69],"possible":[70],"level,":[73],"level":[75],"which":[76],"promotes":[77],"frequent":[78],"occurrences":[79],"structures.":[82],"These":[83],"inferred":[84],"several":[87],"kinds":[88],"information":[90],"used":[92],"correct":[94],"noisy":[95],"data,":[96],"typically":[97],"zoning,":[98],"OCR":[99],"errors":[102],"produced":[103],"previous":[105],"processing":[106],"steps.":[107],"This":[108],"method":[109],"illustrated":[111],"detection":[114],"two":[116,124],"structures:":[118],"page":[119],"numbers":[120],"chapter":[122],"headings,":[123],"navigating":[125],"required":[127],"digital":[129],"libraries.":[130]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}