{"id":"https://openalex.org/W2019222860","doi":"https://doi.org/10.1145/1577802.1577822","title":"Managing multilingual OCR project using XML","display_name":"Managing multilingual OCR project using XML","publication_year":2009,"publication_date":"2009-07-25","ids":{"openalex":"https://openalex.org/W2019222860","doi":"https://doi.org/10.1145/1577802.1577822","mag":"2019222860"},"language":"en","primary_location":{"id":"doi:10.1145/1577802.1577822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1577802.1577822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Multilingual OCR","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/A5025684791","display_name":"Gaurav Harit","orcid":"https://orcid.org/0000-0001-7943-0123"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gaurav Harit","raw_affiliation_strings":["IIT, Kharagpur"],"affiliations":[{"raw_affiliation_string":"IIT, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021301849","display_name":"K. J. Jinesh","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. J. Jinesh","raw_affiliation_strings":["IIIT, Hyderabad","IIIT Hyderabad#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT, Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073906482","display_name":"Ritu Garg","orcid":"https://orcid.org/0000-0003-3227-5036"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ritu Garg","raw_affiliation_strings":["IIT, Delhi","IIT Delhi#TAB#"],"affiliations":[{"raw_affiliation_string":"IIT, Delhi","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"IIT Delhi#TAB#","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["IIIT, Hyderabad","IIIT Hyderabad#TAB#"],"affiliations":[{"raw_affiliation_string":"IIIT, Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086242686","display_name":"Santanu Chaudhury","orcid":"https://orcid.org/0000-0002-5488-7773"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Santanu Chaudhury","raw_affiliation_strings":["IIT, Delhi","IIT Delhi#TAB#"],"affiliations":[{"raw_affiliation_string":"IIT, Delhi","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"IIT Delhi#TAB#","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025684791"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.3428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59450324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9847000241279602,"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":0.982699990272522,"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":0.8329693078994751},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.7251086831092834},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7193248867988586},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5862679481506348},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49722960591316223},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.48670080304145813},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.45659148693084717},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.42172670364379883},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4112203121185303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25354284048080444},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11079376935958862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8329693078994751},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7251086831092834},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7193248867988586},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5862679481506348},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49722960591316223},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.48670080304145813},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45659148693084717},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.42172670364379883},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4112203121185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25354284048080444},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11079376935958862},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1577802.1577822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1577802.1577822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Multilingual OCR","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310119","display_name":"Ministry of Communication and Information Technology","ror":"https://ror.org/05nmnwa45"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W30902120","https://openalex.org/W1590408417","https://openalex.org/W1592017725","https://openalex.org/W1970522460","https://openalex.org/W1988355460","https://openalex.org/W2009339547","https://openalex.org/W2015896468","https://openalex.org/W2078495618","https://openalex.org/W2082163619","https://openalex.org/W2098168725","https://openalex.org/W2113864568","https://openalex.org/W2147510700","https://openalex.org/W2155450843"],"related_works":["https://openalex.org/W2046765700","https://openalex.org/W4384345686","https://openalex.org/W2357937784","https://openalex.org/W2547618384","https://openalex.org/W4394391052","https://openalex.org/W2164215946","https://openalex.org/W2120407907","https://openalex.org/W2016860631","https://openalex.org/W2895456681","https://openalex.org/W4289422041"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"XML-based":[4],"scheme":[5,23],"for":[6,73,80,86],"managing":[7],"a":[8,18,35,52,56],"large":[9,36],"multilingual":[10],"OCR":[11,38,79,89],"project.":[12,33],"In":[13,59],"particular":[14],"we":[15,62],"describe":[16],"how":[17],"new":[19],"XML":[20],"based":[21],"tagging":[22],"has":[24],"been":[25],"exploited":[26],"to":[27],"achieve":[28],"the":[29,32,66,74],"objectives":[30],"of":[31,65,83],"Managing":[34],"multi-lingual":[37],"project":[39,75],"involving":[40],"multiple":[41],"research":[42],"groups,":[43],"developing":[44,78],"script":[45,48],"specific":[46],"and":[47,68],"independent":[49],"technologies":[50],"in":[51],"collaborative":[53],"fashion":[54],"is":[55],"challenging":[57],"problem.":[58],"this":[60],"paper,":[61],"present":[63],"some":[64],"software":[67],"data":[69],"management":[70],"strategies":[71],"designed":[72],"aimed":[76],"at":[77],"11":[81],"scripts":[82],"Indian":[84],"origin":[85],"which":[87],"mature":[88],"technology":[90],"was":[91],"not":[92],"available.":[93]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
