{"id":"https://openalex.org/W2496309551","doi":"https://doi.org/10.1142/9789812775375_0006","title":"EXTRACTION AND MANAGEMENT OF CONTENT FROM HTML DOCUMENTS","display_name":"EXTRACTION AND MANAGEMENT OF CONTENT FROM HTML DOCUMENTS","publication_year":2003,"publication_date":"2003-12-01","ids":{"openalex":"https://openalex.org/W2496309551","doi":"https://doi.org/10.1142/9789812775375_0006","mag":"2496309551"},"language":"en","primary_location":{"id":"doi:10.1142/9789812775375_0006","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812775375_0006","pdf_url":null,"source":{"id":"https://openalex.org/S4210240769","display_name":"Series in machine perception and artificial intelligence","issn_l":"1793-0839","issn":["1793-0839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Series in Machine Perception and Artificial Intelligence","raw_type":"book-chapter"},"type":"book-chapter","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/A5113152319","display_name":"H. Alam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128946","display_name":"BCL Technologies (United States)","ror":"https://ror.org/031ekp611","country_code":"US","type":"company","lineage":["https://openalex.org/I4210128946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Alam","raw_affiliation_strings":["Document Analysis and Recognition Team (DART), BCL Technologies Inc., 990 Linden Drive, Suite # 203, Santa Clara, CA 95050, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Document Analysis and Recognition Team (DART), BCL Technologies Inc., 990 Linden Drive, Suite # 203, Santa Clara, CA 95050, USA","institution_ids":["https://openalex.org/I4210128946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018082511","display_name":"Rachmat Hartono","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128946","display_name":"BCL Technologies (United States)","ror":"https://ror.org/031ekp611","country_code":"US","type":"company","lineage":["https://openalex.org/I4210128946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Hartono","raw_affiliation_strings":["Document Analysis and Recognition Team (DART), BCL Technologies Inc., 990 Linden Drive, Suite # 203, Santa Clara, CA 95050, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Document Analysis and Recognition Team (DART), BCL Technologies Inc., 990 Linden Drive, Suite # 203, Santa Clara, CA 95050, USA","institution_ids":["https://openalex.org/I4210128946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029426102","display_name":"Fuad Rahman","orcid":"https://orcid.org/0000-0002-8670-7124"},"institutions":[{"id":"https://openalex.org/I4210128946","display_name":"BCL Technologies (United States)","ror":"https://ror.org/031ekp611","country_code":"US","type":"company","lineage":["https://openalex.org/I4210128946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. F. R. Rahman","raw_affiliation_strings":["Document Analysis and Recognition Team (DART), BCL Technologies Inc., 990 Linden Drive, Suite # 203, Santa Clara, CA 95050, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Document Analysis and Recognition Team (DART), BCL Technologies Inc., 990 Linden Drive, Suite # 203, Santa Clara, CA 95050, USA","institution_ids":["https://openalex.org/I4210128946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7543,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76392055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.41200000047683716,"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":0.41200000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5998660922050476},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5479635000228882},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5456534028053284},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3244745135307312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13402268290519714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5998660922050476},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5479635000228882},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5456534028053284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3244745135307312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13402268290519714},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/9789812775375_0006","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812775375_0006","pdf_url":null,"source":{"id":"https://openalex.org/S4210240769","display_name":"Series in machine perception and artificial intelligence","issn_l":"1793-0839","issn":["1793-0839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Series in Machine Perception and Artificial Intelligence","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
