{"id":"https://openalex.org/W2035439590","doi":"https://doi.org/10.1145/1096601.1096605","title":"Structuring documents according to their table of contents","display_name":"Structuring documents according to their table of contents","publication_year":2005,"publication_date":"2005-11-02","ids":{"openalex":"https://openalex.org/W2035439590","doi":"https://doi.org/10.1145/1096601.1096605","mag":"2035439590"},"language":"en","primary_location":{"id":"doi:10.1145/1096601.1096605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1096601.1096605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 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/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":3.283,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92683069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9966999888420105,"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":"Handwritten Text Recognition Techniques","score":0.9966999888420105,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9955999851226807,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9955000281333923,"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/structuring","display_name":"Structuring","score":0.9545964002609253},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7205144166946411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7179625630378723},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6019866466522217},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5848140716552734},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4935554265975952},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4779945909976959},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.46805232763290405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35101836919784546},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10254347324371338}],"concepts":[{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.9545964002609253},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7205144166946411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179625630378723},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6019866466522217},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5848140716552734},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4935554265975952},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4779945909976959},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.46805232763290405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35101836919784546},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10254347324371338},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1096601.1096605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1096601.1096605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.8183","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.8183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.xrce.xerox.com/Publications/Attachments/2005-002/fp10640-dejean.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":14,"referenced_works":["https://openalex.org/W1589867711","https://openalex.org/W1991334432","https://openalex.org/W1992419399","https://openalex.org/W2094193200","https://openalex.org/W2105413446","https://openalex.org/W2113119530","https://openalex.org/W2115927545","https://openalex.org/W2128762945","https://openalex.org/W2130367588","https://openalex.org/W2134590793","https://openalex.org/W2137526383","https://openalex.org/W2142384583","https://openalex.org/W2170066740","https://openalex.org/W6679270147"],"related_works":["https://openalex.org/W1671988510","https://openalex.org/W2097798129","https://openalex.org/W2394344929","https://openalex.org/W4299352401","https://openalex.org/W2116763882","https://openalex.org/W2327961366","https://openalex.org/W2026588654","https://openalex.org/W1863997242","https://openalex.org/W2120400243","https://openalex.org/W2128762945"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4,15],"a":[5,9,43],"method":[6,69],"for":[7],"structuring":[8],"document":[10,39],"according":[11],"to":[12,36],"the":[13,24,29,32,38,63,68],"information":[14],"in":[16,37,73],"its":[17,52],"Table":[18],"of":[19,23,31,45,67,75],"Contents.":[20],"The":[21],"detection":[22],"ToC":[25],"as":[26,28],"well":[27],"determination":[30],"parts":[33],"it":[34],"refers":[35],"body":[40],"rely":[41],"on":[42,62],"series":[44],"generic":[46],"properties":[47],"characterizing":[48],"any":[49],"ToC,":[50],"while":[51],"hierarchization":[53],"is":[54],"achieved":[55],"using":[56],"clustering":[57],"techniques.":[58],"We":[59],"also":[60],"report":[61],"robustness":[64],"and":[65],"performance":[66],"before":[70],"discussing":[71],"it,":[72],"light":[74],"related":[76],"work.":[77]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}