{"id":"https://openalex.org/W2023146846","doi":"https://doi.org/10.1145/1030397.1030439","title":"Supervised learning for the legacy document conversion","display_name":"Supervised learning for the legacy document conversion","publication_year":2004,"publication_date":"2004-10-28","ids":{"openalex":"https://openalex.org/W2023146846","doi":"https://doi.org/10.1145/1030397.1030439","mag":"2023146846"},"language":"en","primary_location":{"id":"doi:10.1145/1030397.1030439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1030397.1030439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM symposium on Document engineering","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/A5046897413","display_name":"Boris Chidlovskii","orcid":"https://orcid.org/0000-0002-2958-2361"},"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":"Boris Chidlovskii","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/A5002635173","display_name":"J\u00e9r\u00f4me Fuselier","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":"J\u00e9r\u00f4me Fuselier","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/A5046897413"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":null,"apc_paid":null,"fwci":4.0374,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.94014769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9966999888420105,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8365830183029175},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7979978919029236},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6711763739585876},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.5875738263130188},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5401822924613953},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.4922696650028229},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.46225637197494507},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4432850480079651},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.44018983840942383},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.4303722381591797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42587268352508545},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3648058772087097},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.32265666127204895},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11820009350776672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08536559343338013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8365830183029175},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7979978919029236},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6711763739585876},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.5875738263130188},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5401822924613953},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.4922696650028229},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.46225637197494507},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4432850480079651},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.44018983840942383},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.4303722381591797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42587268352508545},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3648058772087097},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.32265666127204895},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11820009350776672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08536559343338013},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1030397.1030439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1030397.1030439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.105.8804","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.105.8804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.syscom.univ-savoie.fr/publi/Chidlovskii2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1504436033","https://openalex.org/W1529355025","https://openalex.org/W1553229631","https://openalex.org/W1768003599","https://openalex.org/W1934019294","https://openalex.org/W1983284692","https://openalex.org/W1990483472","https://openalex.org/W1995362929","https://openalex.org/W2030241598","https://openalex.org/W2070046067","https://openalex.org/W2070386554","https://openalex.org/W2096152098","https://openalex.org/W2096175520","https://openalex.org/W2121227244","https://openalex.org/W2134222424","https://openalex.org/W2136500370","https://openalex.org/W2155758288","https://openalex.org/W2164765168","https://openalex.org/W2560674852","https://openalex.org/W2561675875","https://openalex.org/W2603514790","https://openalex.org/W4211138600","https://openalex.org/W6631608000","https://openalex.org/W6637894171","https://openalex.org/W6678277124"],"related_works":["https://openalex.org/W2352672621","https://openalex.org/W4206399782","https://openalex.org/W1895313402","https://openalex.org/W2181356758","https://openalex.org/W4283736786","https://openalex.org/W1592776645","https://openalex.org/W2011024487","https://openalex.org/W3022924207","https://openalex.org/W52357592","https://openalex.org/W2111753772"],"abstract_inverted_index":{"We":[0,25,49,80,106],"consider":[1],"the":[2,8,37,51,56,62,75,86,94,103,112,116,127],"problem":[3],"of":[4,46,70,74,77,111],"document":[5],"conversion":[6,38,57,87],"from":[7,67,102],"rendering-oriented":[9],"HTML":[10],"markup":[11],"into":[12],"a":[13,44,68,82],"semantic-oriented":[14],"XML":[15,22],"annotation":[16],"defined":[17],"by":[18,42],"user-specific":[19],"DTDs":[20],"or":[21],"Schema":[23],"descriptions.":[24],"represent":[26],"both":[27],"source":[28,95],"and":[29,97,119,132],"target":[30,100,117],"documents":[31],"as":[32],"rooted":[33],"ordered":[34],"trees":[35,96,101],"so":[36],"can":[39],"be":[40],"achieved":[41],"applying":[43],"set":[45,69],"tree":[47,63],"transformations.":[48],"apply":[50],"supervised":[52],"learning":[53],"framework":[54],"to":[55,60,85],"task":[58],"according":[59],"which":[61],"transformations":[64],"are":[65],"learned":[66],"training":[71],"examples.":[72],"%Because":[73],"complexity":[76],"tree-to-tree":[78],"transformations,":[79],"develop":[81,123],"two-step":[83],"approach":[84],"problem,":[88],"that":[89],"first":[90],"labels":[91],"leaves":[92],"in":[93],"then":[98],"recomposes":[99],"leaf":[104,113,128],"labels.":[105],"present":[107],"two":[108,138],"solutions":[109,133],"based":[110],"classification":[114],"with":[115],"terminals":[118],"paths.":[120],"Moreover,":[121],"we":[122],"three":[124],"methods":[125,131],"for":[126],"classification.":[129],"All":[130],"have":[134],"been":[135],"tested":[136],"on":[137],"real":[139],"collections.":[140]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}