{"id":"https://openalex.org/W1602839414","doi":"https://doi.org/10.1109/icdar.2003.1227667","title":"Automatic discovery of semantic structures in HTML documents","display_name":"Automatic discovery of semantic structures in HTML documents","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W1602839414","doi":"https://doi.org/10.1109/icdar.2003.1227667","mag":"1602839414"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2003.1227667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5042437692","display_name":"Saikat Mukherjee","orcid":"https://orcid.org/0000-0002-4637-445X"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Mukherjee","raw_affiliation_strings":["Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","Department of Computer Science, State University of New York, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102081605","display_name":"Guizhen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guizhen Yang","raw_affiliation_strings":["Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","Department of Computer Science, State University of New York, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090696764","display_name":"Wenfang Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenfang Tan","raw_affiliation_strings":["Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","Department of Computer Science, State University of New York, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005648942","display_name":"I. V. Ramakrishnan","orcid":"https://orcid.org/0000-0002-1768-7043"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I.V. Ramakrishnan","raw_affiliation_strings":["Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","Department of Computer Science, State University of New York, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4486,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9284311,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"245","last_page":"249"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9958999752998352,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8582515716552734},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7192736864089966},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6932433843612671},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5568422675132751},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5053213238716125},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4100436866283417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3762076497077942},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.225594162940979},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.14258480072021484},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08337107300758362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582515716552734},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7192736864089966},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6932433843612671},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5568422675132751},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5053213238716125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4100436866283417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3762076497077942},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.225594162940979},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.14258480072021484},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08337107300758362},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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:10.1109/icdar.2003.1227667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.8986","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.8986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.sri.com/~yang/papers/icdar2003.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W193121434","https://openalex.org/W1664954303","https://openalex.org/W1927338256","https://openalex.org/W1990483472","https://openalex.org/W2060918911","https://openalex.org/W2093559286","https://openalex.org/W2095680579","https://openalex.org/W2108350934","https://openalex.org/W2116493296","https://openalex.org/W2134356404","https://openalex.org/W2147100344","https://openalex.org/W2155758288"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W1556451512","https://openalex.org/W1971913216","https://openalex.org/W4234091740","https://openalex.org/W4213350282","https://openalex.org/W2230171082","https://openalex.org/W2583128298","https://openalex.org/W2369125128","https://openalex.org/W2134423494","https://openalex.org/W2923292609"],"abstract_inverted_index":{"Template-driven":[0],"HTML":[1,35],"documents":[2,36],"possess":[3],"an":[4,42],"implicit,":[5],"fixed":[6],"schema":[7,19],"denoting":[8],"concepts":[9],"and":[10],"their":[11],"relationships":[12],"in":[13,34],"a":[14,21,27],"hierarchical":[15],"fashion.":[16],"Discovering":[17],"this":[18],"remains":[20],"relatively":[22],"unexplored":[23],"problem.":[24],"By":[25],"exploiting":[26],"key":[28],"observation":[29],"that":[30],"semantically":[31],"related":[32],"items":[33],"exhibit":[37],"spatial":[38],"locality,":[39],"we":[40],"develop":[41],"algorithm":[43],"for":[44],"automatically":[45],"partitioning":[46],"them":[47],"into":[48],"tree-like":[49],"semantic":[50],"structures":[51],"which":[52],"expose":[53],"the":[54],"implicit":[55],"schema.":[56]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}