{"id":"https://openalex.org/W1506984360","doi":"https://doi.org/10.1007/978-3-540-39718-2_34","title":"Automatic Annotation of Content-Rich HTML Documents: Structural and Semantic Analysis","display_name":"Automatic Annotation of Content-Rich HTML Documents: Structural and Semantic Analysis","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1506984360","doi":"https://doi.org/10.1007/978-3-540-39718-2_34","mag":"1506984360"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-39718-2_34","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-540-39718-2_34","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-540-39718-2_34.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-540-39718-2_34.pdf","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/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":true,"raw_author_name":"Saikat Mukherjee","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794, U.S.A","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102081605","display_name":"Guizhen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guizhen Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, 14260, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, 14260, U.S.A","institution_ids":["https://openalex.org/I63190737"]}]},{"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/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, Stony Brook University, Stony Brook, NY, 11794, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794, U.S.A","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042437692"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":7.771,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97571524,"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":"533","last_page":"549"},"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":0.9767000079154968,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9613999724388123,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9211057424545288},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6839377880096436},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.4987640380859375},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4687032401561737},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.46455854177474976},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.45952826738357544},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.4566485285758972},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.4411900043487549},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4364240765571594},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.4249686598777771},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.4159570336341858},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3574875593185425},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.22254812717437744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9211057424545288},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6839377880096436},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.4987640380859375},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4687032401561737},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.46455854177474976},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.45952826738357544},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.4566485285758972},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.4411900043487549},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4364240765571594},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.4249686598777771},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.4159570336341858},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3574875593185425},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.22254812717437744}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-39718-2_34","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-540-39718-2_34","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-540-39718-2_34.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-540-39718-2_34","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-540-39718-2_34","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-540-39718-2_34.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2080576861","display_name":"ITR: Model Checking for Detecting Computer System Vulnerabilities","funder_award_id":"0205376","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4107515145","display_name":"A Deductive Engine for the Semantic Web","funder_award_id":"0311512","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8939264893","display_name":"Logic-based Modeling Analysis, and Implementation of Workflow Management Systems","funder_award_id":"0072927","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1506984360.pdf","grobid_xml":"https://content.openalex.org/works/W1506984360.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W98819805","https://openalex.org/W1475165414","https://openalex.org/W1535411693","https://openalex.org/W1540347473","https://openalex.org/W1565133950","https://openalex.org/W1576923525","https://openalex.org/W1803241704","https://openalex.org/W1905489744","https://openalex.org/W1911479129","https://openalex.org/W1927338256","https://openalex.org/W1990483472","https://openalex.org/W2010500834","https://openalex.org/W2013848664","https://openalex.org/W2049205525","https://openalex.org/W2074277560","https://openalex.org/W2076129550","https://openalex.org/W2085016361","https://openalex.org/W2093559286","https://openalex.org/W2095680579","https://openalex.org/W2104086170","https://openalex.org/W2104972336","https://openalex.org/W2108350934","https://openalex.org/W2116493296","https://openalex.org/W2128836931","https://openalex.org/W2134356404","https://openalex.org/W2135317768","https://openalex.org/W2147100344","https://openalex.org/W2149033849","https://openalex.org/W2150721933","https://openalex.org/W2155758288","https://openalex.org/W2166407869","https://openalex.org/W2169347997","https://openalex.org/W2169463693","https://openalex.org/W2483562931","https://openalex.org/W2952727465","https://openalex.org/W4233527139","https://openalex.org/W4245031736","https://openalex.org/W4248809068","https://openalex.org/W4250974719","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2387349142","https://openalex.org/W4206751470","https://openalex.org/W1582561301","https://openalex.org/W146038348","https://openalex.org/W2093676590","https://openalex.org/W2128878007","https://openalex.org/W2087715630","https://openalex.org/W2348459908","https://openalex.org/W2373083285","https://openalex.org/W2341454089"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}