{"id":"https://openalex.org/W2071448315","doi":"https://doi.org/10.1109/icdar.2007.4378704","title":"Web Document Parsing: A New Approach to Modeling Layout-Language Relations","display_name":"Web Document Parsing: A New Approach to Modeling Layout-Language Relations","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2071448315","doi":"https://doi.org/10.1109/icdar.2007.4378704","mag":"2071448315"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4378704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378704","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","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/A5072121765","display_name":"Mikio Yoshida","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"M. Yoshida","raw_affiliation_strings":["Information Technology Centre, University of Tokyo, Bunkyo, Tokyo, Japan","University of Tokyo, Tokyo,"],"affiliations":[{"raw_affiliation_string":"Information Technology Centre, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Tokyo, Tokyo,","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Nakagawa","raw_affiliation_strings":["Information Technology Centre, University of Tokyo, Bunkyo, Tokyo, Japan","University of Tokyo, Tokyo,"],"affiliations":[{"raw_affiliation_string":"Information Technology Centre, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Tokyo, Tokyo,","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072121765"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.1118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76682529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9962999820709229,"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":0.8892350196838379},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7368984818458557},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6494134068489075},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.64866042137146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6185452938079834},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5534065365791321},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5474317073822021},{"id":"https://openalex.org/keywords/synchronous-context-free-grammar","display_name":"Synchronous context-free grammar","score":0.4667065143585205},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.41827359795570374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3825797438621521},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.35302579402923584},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18835783004760742},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0880383849143982}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8892350196838379},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7368984818458557},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6494134068489075},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.64866042137146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6185452938079834},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5534065365791321},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5474317073822021},{"id":"https://openalex.org/C51802942","wikidata":"https://www.wikidata.org/wiki/Q7662211","display_name":"Synchronous context-free grammar","level":4,"score":0.4667065143585205},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.41827359795570374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3825797438621521},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.35302579402923584},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18835783004760742},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0880383849143982},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2007.4378704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378704","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1602839414","https://openalex.org/W1988926831","https://openalex.org/W2095680579","https://openalex.org/W2104086170","https://openalex.org/W2114535528","https://openalex.org/W2145076056","https://openalex.org/W2155758288","https://openalex.org/W2160050794","https://openalex.org/W2160196229","https://openalex.org/W2164732909","https://openalex.org/W6675573929"],"related_works":["https://openalex.org/W2118045671","https://openalex.org/W2166769824","https://openalex.org/W1656514314","https://openalex.org/W318813979","https://openalex.org/W2106477919","https://openalex.org/W2076046700","https://openalex.org/W4245826738","https://openalex.org/W2109871145","https://openalex.org/W2099851297","https://openalex.org/W2163454936"],"abstract_inverted_index":{"We":[0,25],"propose":[1],"a":[2],"novel":[3],"approach":[4,45],"for":[5,29],"extracting":[6],"semantic":[7],"structures":[8],"from":[9],"Web":[10],"documents.":[11,24],"Our":[12],"task":[13,31],"is":[14],"to":[15],"extract":[16],"trees":[17],"that":[18,43],"describe":[19],"the":[20,34,52],"hierarchical":[21],"relations":[22],"in":[23],"developed":[26],"an":[27],"algorithm":[28],"this":[30],"by":[32],"using":[33],"stochastic":[35],"context":[36],"free":[37],"grammar":[38],"(SCFG)":[39],"framework.":[40],"Experiments":[41],"showed":[42],"our":[44],"effectively":[46],"worked":[47],"showing":[48],"performance":[49],"improvement":[50],"through":[51],"parameter":[53],"estimation.":[54]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}