{"id":"https://openalex.org/W180578023","doi":null,"title":"Stochastic models for document restructuration","display_name":"Stochastic models for document restructuration","publication_year":2005,"publication_date":"2005-10-03","ids":{"openalex":"https://openalex.org/W180578023","mag":"180578023"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.102.5182","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.102.5182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.pascal-network.org/archive/00000183/01/2005-ecml-Wshop-Gallinari.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5113667126","display_name":"Patrick Gallinari","orcid":"https://orcid.org/0000-0001-9060-9001","observed_orcids":["https://orcid.org/0000-0001-9060-9001"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Gallinari","raw_affiliation_strings":["Machine Learning and Information Retrieval"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and Information Retrieval","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013670630","display_name":"Guillaume Wisniewski","orcid":"https://orcid.org/0000-0002-4445-080X","observed_orcids":["https://orcid.org/0000-0002-4445-080X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Wisniewski","raw_affiliation_strings":["Machine Learning and Information Retrieval"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and Information Retrieval","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027101473","display_name":"Ludovic Denoyer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ludovic Denoyer","raw_affiliation_strings":["Machine Learning and Information Retrieval"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and Information Retrieval","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056955528","display_name":"Francis Maes","orcid":"https://orcid.org/0000-0003-0442-2748","observed_orcids":["https://orcid.org/0000-0003-0442-2748"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francis Maes","raw_affiliation_strings":["Machine Learning and Information Retrieval"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and Information Retrieval","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lip Universit\u00e9","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lip Universit\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pierre Marie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Marie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Curie Paris- France","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Curie Paris- France","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7283,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87878301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.8910999894142151,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.8910999894142151,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.024900000542402267,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.01209999993443489,"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/semistructured-data","display_name":"semi-structured data","score":0.8080000281333923},{"id":"https://openalex.org/keywords/stochastic-modeling","display_name":"stochastic modeling","score":0.8029999732971191},{"id":"https://openalex.org/keywords/document-structuring","display_name":"document structuring","score":0.5350000262260437},{"id":"https://openalex.org/keywords/heterogeneous-databases","display_name":"heterogeneous databases","score":0.6660000085830688},{"id":"https://openalex.org/keywords/xml-retrieval","display_name":"XML retrieval","score":0.6980000138282776},{"id":"https://openalex.org/keywords/peer-to-peer-networks","display_name":"peer-to-peer networks","score":0.8790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8950307369232178},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6979976892471313},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6933746337890625},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.63017737865448},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5873794555664062},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.45876187086105347},{"id":"https://openalex.org/C137441365","wikidata":"https://www.wikidata.org/wiki/Q7981054","display_name":"Well-formed document","level":5,"score":0.4407896399497986},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.43494898080825806},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3287312388420105},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.3202991485595703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14467853307724},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.102.5182","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.102.5182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.pascal-network.org/archive/00000183/01/2005-ecml-Wshop-Gallinari.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01357589v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-01357589","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ECML'05 Workshop on Relationnal Machine Learning, Oct 2005, Porto, Portugal","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W35277665","https://openalex.org/W118635492","https://openalex.org/W1519066168","https://openalex.org/W1551104980","https://openalex.org/W1568850833","https://openalex.org/W1593317353","https://openalex.org/W1636244751","https://openalex.org/W2023146846","https://openalex.org/W2138105615","https://openalex.org/W2143774317","https://openalex.org/W2163915185","https://openalex.org/W2429914308"],"related_works":["https://openalex.org/W1578345858","https://openalex.org/W1998655283","https://openalex.org/W52043909","https://openalex.org/W2375670974","https://openalex.org/W1517261689","https://openalex.org/W118635492","https://openalex.org/W7095284325","https://openalex.org/W2169366756","https://openalex.org/W120184336","https://openalex.org/W171296176"],"abstract_inverted_index":{"Abstract-":[0],"Document":[1],"(re)structuration":[2],"consists":[3],"in":[4,23],"mapping":[5],"documents":[6,73],"coming":[7],"from":[8,50],"different":[9,12,24],"sources,":[10],"with":[11],"formats,":[13],"onto":[14],"a":[15,51,93],"predefined":[16],"semistructured":[17],"format.":[18],"This":[19],"generic":[20],"problem":[21,49],"appears":[22],"applications":[25],"settings":[26],"like":[27],"heterogeneous":[28],"semi-structured":[29],"databases":[30],"querying,":[31],"peer":[32,34],"to":[33],"systems,":[35],"legacy":[36],"document":[37,52,96],"conversion,":[38],"XML":[39,95],"information":[40],"retrieval.":[41],"In":[42],"the":[43,47,57,76],"paper,":[44],"we":[45],"define":[46],"restructuration":[48,69],"centric":[53],"perspective":[54],"and":[55,74,89],"identify":[56],"main":[58],"problems":[59],"raised":[60],"by":[61],"this":[62],"new":[63],"problematic.":[64],"We":[65,81],"then":[66],"consider":[67],"two":[68,87],"instances:":[70],"structuring":[71],"flat":[72],"learning":[75],"correspondence":[77],"between":[78],"structured":[79],"formats.":[80],"propose":[82],"stochastic":[83],"models":[84],"for":[85],"these":[86],"tasks":[88],"describe":[90],"tests":[91],"on":[92],"large":[94],"collection.":[97],"1.":[98]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2016-06-24T00:00:00"}