{"id":"https://openalex.org/W2375670974","doi":null,"title":"Probabilistic Model for Structured Document Mapping Application to Automatic HTML to XML Conversion","display_name":"Probabilistic Model for Structured Document Mapping Application to Automatic HTML to XML Conversion","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2375670974","mag":"2375670974"},"language":"en","primary_location":{"id":"mag:2375670974","doi":null,"is_oa":false,"landing_page_url":"http://www-connex.lip6.fr/~denoyer/ATASH_public/uploads/Lot3/2.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"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/A5013670630","display_name":"Guillaume Wisniewski","orcid":"https://orcid.org/0000-0002-4445-080X","observed_orcids":["https://orcid.org/0000-0002-4445-080X"]},"institutions":[{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Wisniewski","raw_affiliation_strings":["Accueil LIP6"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Accueil LIP6","institution_ids":["https://openalex.org/I4210159731"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035651557","display_name":"Frederik Maes","orcid":"https://orcid.org/0000-0003-0027-1479","observed_orcids":["https://orcid.org/0000-0003-0027-1479"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frederik Maes","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0027-1479","affiliations":[]},{"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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.6323000192642212,"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":0.6323000192642212,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.14589999616146088,"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":0.07569999992847443,"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/html-to-xml-conversion","display_name":"HTML to XML conversion","score":0.8550000190734863},{"id":"https://openalex.org/keywords/semi-structured-documents","display_name":"semi-structured documents","score":0.9539999961853027},{"id":"https://openalex.org/keywords/generative-probabilistic-models","display_name":"probabilistic generative models","score":0.6159999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.868808925151825},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.7545661926269531},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6291586756706238},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5712142586708069},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5619332790374756},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5376189351081848},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5336079597473145},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.47847792506217957},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.47327470779418945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46777477860450745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45899417996406555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43084433674812317},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4267650544643402},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.4022008776664734},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1369936466217041},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2375670974","doi":null,"is_oa":false,"landing_page_url":"http://www-connex.lip6.fr/~denoyer/ATASH_public/uploads/Lot3/2.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W118635492","https://openalex.org/W1519066168","https://openalex.org/W1560635010","https://openalex.org/W1593317353","https://openalex.org/W1636244751","https://openalex.org/W1874182309","https://openalex.org/W2010624529","https://openalex.org/W2023146846","https://openalex.org/W2069140227","https://openalex.org/W2096175520","https://openalex.org/W2102667697","https://openalex.org/W2138105615","https://openalex.org/W2143774317","https://openalex.org/W2155758288","https://openalex.org/W2169366756","https://openalex.org/W2626905489"],"related_works":["https://openalex.org/W1517261689","https://openalex.org/W1545716422","https://openalex.org/W25889855","https://openalex.org/W2169366756","https://openalex.org/W7095284325","https://openalex.org/W52043909","https://openalex.org/W1998655283","https://openalex.org/W7096038374","https://openalex.org/W69822821","https://openalex.org/W4296765674"],"abstract_inverted_index":{"We":[0,18,41,97],"address":[1],"the":[2,25,60,82,86,103,107],"problem":[3],"of":[4,39,48,62,95,102,111],"learning":[5,22],"automatically":[6],"to":[7,80,113],"map":[8],"heterogeneous":[9],"semi-structured":[10],"documents":[11,32,52,88],"onto":[12],"a":[13,20,36,44,66,70,92,129],"mediated":[14],"target":[15,31,75],"XML":[16,114],"schema.":[17],"adopt":[19],"machine":[21],"approach":[23],"where":[24],"mapping":[26],"be-":[27],"tween":[28],"input":[29,73,87],"and":[30,54,74,133],"is":[33,65,118],"learned":[34],"from":[35],"training":[37],"corpus":[38],"documents.":[40,76],"first":[42],"introduce":[43],"general":[45,104],"stochastic":[46],"model":[47,57,105],"semi":[49],"struc-":[50],"tured":[51],"generation":[53],"transformation.":[55],"This":[56,116],"relies":[58],"on":[59,120],"concept":[61],"meta-document":[63],"which":[64],"latent":[67],"variable":[68],"providing":[69],"link":[71],"between":[72],"It":[77],"allows":[78],"us":[79],"learn":[81],"corre-":[83],"spondences":[84],"when":[85],"are":[89],"expressed":[90],"in":[91],"large":[93],"variety":[94],"schemas.":[96],"then":[98],"detail":[99],"an":[100,134],"instance":[101,117],"for":[106],"par-":[108],"ticular":[109],"task":[110],"HTML":[112],"conversion.":[115],"tested":[119],"three":[121],"different":[122,126],"corpora":[123],"using":[124],"two":[125],"inference":[127],"methods:":[128],"dynamic":[130],"programming":[131],"method":[132],"approximate":[135],"LaSO-based":[136],"method.":[137]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}