{"id":"https://openalex.org/W2090193136","doi":"https://doi.org/10.1145/1860559.1860590","title":"Document structure meets page layout","display_name":"Document structure meets page layout","publication_year":2010,"publication_date":"2010-09-21","ids":{"openalex":"https://openalex.org/W2090193136","doi":"https://doi.org/10.1145/1860559.1860590","mag":"2090193136"},"language":"en","primary_location":{"id":"doi:10.1145/1860559.1860590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1860559.1860590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"preprint","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/A5066703422","display_name":"Alex Spengler","orcid":null},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alex Spengler","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113667126","display_name":"Patrick Gallinari","orcid":"https://orcid.org/0000-0003-3360-8269"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Gallinari","raw_affiliation_strings":["Universit\u00e9 Pierre et Marie Curie, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Pierre et Marie Curie, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066703422"],"corresponding_institution_ids":["https://openalex.org/I39804081"],"apc_list":null,"apc_paid":null,"fwci":4.3214,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95001266,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T13976","display_name":"Web visibility and informetrics","score":0.9760000109672546,"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":0.9332000017166138,"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":0.8613680601119995},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.677016019821167},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6277334690093994},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5820537805557251},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5453330278396606},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5433131456375122},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5263087749481201},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4514731764793396},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35877418518066406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23635870218276978},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08190479874610901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613680601119995},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.677016019821167},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6277334690093994},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5820537805557251},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5453330278396606},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5433131456375122},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5263087749481201},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4514731764793396},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35877418518066406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23635870218276978},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08190479874610901},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1860559.1860590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1860559.1860590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00637719v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00637719","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"10th ACM Symposium on Document Engineering (DocEng 2010), Sep 2010, Manchester, United Kingdom. pp.151-160, &#x27E8;10.1145/1860559.1860590&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W15548","https://openalex.org/W116870935","https://openalex.org/W1560512119","https://openalex.org/W1583837637","https://openalex.org/W1803802947","https://openalex.org/W1991565788","https://openalex.org/W2005646337","https://openalex.org/W2007442002","https://openalex.org/W2019264297","https://openalex.org/W2049781914","https://openalex.org/W2051141368","https://openalex.org/W2072489225","https://openalex.org/W2078951877","https://openalex.org/W2084358158","https://openalex.org/W2088600132","https://openalex.org/W2101909884","https://openalex.org/W2109189215","https://openalex.org/W2110606009","https://openalex.org/W2116294498","https://openalex.org/W2120101509","https://openalex.org/W2135997060","https://openalex.org/W2137213923","https://openalex.org/W2139830916","https://openalex.org/W2140208587","https://openalex.org/W2147880316","https://openalex.org/W2160069741","https://openalex.org/W2165094554","https://openalex.org/W2913318000","https://openalex.org/W2962735828","https://openalex.org/W2994982620","https://openalex.org/W2999905431","https://openalex.org/W6600000387","https://openalex.org/W6676463157","https://openalex.org/W6771369255"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W2372091777","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173","https://openalex.org/W1544491176","https://openalex.org/W2185387300"],"abstract_inverted_index":{"Web":[0],"content":[1],"extraction":[2],"is":[3,23,83],"concerned":[4],"with":[5,109],"the":[6,29,40,46,87,133],"automatic":[7],"identification":[8],"of":[9,32,77,93,100,120,137],"semantically":[10,134],"interesting":[11,135],"web":[12,35,103,139],"page":[13,36,71],"regions.":[14],"To":[15],"generalize":[16],"to":[17,25,127],"pages":[18,104],"from":[19,66,105],"unknown":[20],"sites,":[21],"it":[22],"crucial":[24],"exploit":[26],"not":[27],"only":[28],"local":[30,78],"characteristics":[31],"a":[33,55,74,98,128,138],"particular":[34],"region,":[37],"but":[38],"also":[39],"rich":[41],"interdependencies":[42,125],"that":[43,117],"exist":[44],"between":[45],"regions":[47,136],"and":[48,70,79,82,123],"their":[49],"latent":[50],"semantics.":[51],"We":[52],"therefore":[53],"propose":[54],"loopy":[56],"conditional":[57],"random":[58],"field":[59],"which":[60],"combines":[61],"semantic":[62],"intra-page":[63],"dependencies":[64],"derived":[65],"both":[67],"document":[68,121],"structure":[69,122],"layout,":[72],"uses":[73],"realistic":[75],"set":[76],"relational":[80],"features":[81],"efficiently":[84],"learnt":[85],"in":[86],"tree-based":[88],"reparameterization":[89],"framework.":[90],"The":[91],"results":[92],"our":[94,118],"empirical":[95],"analysis":[96],"on":[97,112,132],"corpus":[99],"real-world":[101],"news":[102],"177":[106],"distinct":[107],"sites":[108],"multiple":[110],"annotations":[111],"DOM":[113],"node":[114],"level":[115],"demonstrate":[116],"combination":[119],"layout-driven":[124],"leads":[126],"significant":[129],"error":[130],"reduction":[131],"page.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}
