{"id":"https://openalex.org/W2094547787","doi":"https://doi.org/10.1007/s00799-004-0082-z","title":"A Hierarchical Extraction Policy for content extraction signatures","display_name":"A Hierarchical Extraction Policy for content extraction signatures","publication_year":2004,"publication_date":"2004-10-19","ids":{"openalex":"https://openalex.org/W2094547787","doi":"https://doi.org/10.1007/s00799-004-0082-z","mag":"2094547787"},"language":"en","primary_location":{"id":"doi:10.1007/s00799-004-0082-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-004-0082-z","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/report/A_Hierarchical_Extraction_Policy_for_Content_Extraction_Signatures/20707477","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025881765","display_name":"Laurence Bull","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140999","display_name":"Dandenong Hospital","ror":"https://ror.org/046gme853","country_code":"AU","type":"healthcare","lineage":["https://openalex.org/I4210121067","https://openalex.org/I4210140999"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Laurence Bull","raw_affiliation_strings":["School of Computer Science and Software Engineering, Monash University, 900 Dandenong Road, Caulfield, Victoria, 3145, Australia","Monash University, School of Computer Science and Software Engineering, 900 Dandenong Road, 3145, Caulfield, Victoria, Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Monash University, 900 Dandenong Road, Caulfield, Victoria, 3145, Australia","institution_ids":["https://openalex.org/I4210140999"]},{"raw_affiliation_string":"Monash University, School of Computer Science and Software Engineering, 900 Dandenong Road, 3145, Caulfield, Victoria, Australia#TAB#","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032303916","display_name":"David Squire","orcid":"https://orcid.org/0000-0001-6738-8271"},"institutions":[{"id":"https://openalex.org/I4210140999","display_name":"Dandenong Hospital","ror":"https://ror.org/046gme853","country_code":"AU","type":"healthcare","lineage":["https://openalex.org/I4210121067","https://openalex.org/I4210140999"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David McG. Squire","raw_affiliation_strings":["School of Computer Science and Software Engineering, Monash University, 900 Dandenong Road, Caulfield, Victoria, 3145, Australia","Monash University, School of Computer Science and Software Engineering, 900 Dandenong Road, 3145, Caulfield, Victoria, Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Monash University, 900 Dandenong Road, Caulfield, Victoria, 3145, Australia","institution_ids":["https://openalex.org/I4210140999"]},{"raw_affiliation_string":"Monash University, School of Computer Science and Software Engineering, 900 Dandenong Road, 3145, Caulfield, Victoria, Australia#TAB#","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000813695","display_name":"Yuliang Zheng","orcid":"https://orcid.org/0000-0002-9815-9727"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuliang Zheng","raw_affiliation_strings":["Department of Software and Information Systems, University of North Carolina at Charlotte, Charlotte, NC, 28223, USA","University of North Carolina at Charlotte, Department of Software and Information Systems, 900 Dandenong Road, 28223, Charlotte, NC, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software and Information Systems, University of North Carolina at Charlotte, Charlotte, NC, 28223, USA","institution_ids":["https://openalex.org/I102149020"]},{"raw_affiliation_string":"University of North Carolina at Charlotte, Department of Software and Information Systems, 900 Dandenong Road, 28223, Charlotte, NC, USA#TAB#","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025881765"],"corresponding_institution_ids":["https://openalex.org/I4210140999","https://openalex.org/I56590836"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":1.5997,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87909574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"4","issue":"3","first_page":"208","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.9987000226974487,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9936000108718872,"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"}},{"id":"https://openalex.org/T13999","display_name":"Digital Rights Management and Security","score":0.9919000267982483,"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":0.8677101135253906},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7552670240402222},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5175654292106628},{"id":"https://openalex.org/keywords/digital-signature","display_name":"Digital signature","score":0.4894324839115143},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.47351980209350586},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.425426185131073},{"id":"https://openalex.org/keywords/digital-content","display_name":"Digital content","score":0.42495396733283997},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.41512182354927063},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37079036235809326},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3415883183479309},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2873186469078064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13753584027290344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07692143321037292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677101135253906},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7552670240402222},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5175654292106628},{"id":"https://openalex.org/C118463975","wikidata":"https://www.wikidata.org/wiki/Q220849","display_name":"Digital signature","level":3,"score":0.4894324839115143},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.47351980209350586},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.425426185131073},{"id":"https://openalex.org/C2779344036","wikidata":"https://www.wikidata.org/wiki/Q11320476","display_name":"Digital content","level":2,"score":0.42495396733283997},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.41512182354927063},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37079036235809326},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3415883183479309},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2873186469078064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13753584027290344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07692143321037292},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s00799-004-0082-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00799-004-0082-z","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.112.9474","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.112.9474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sis.uncc.edu/~yzheng/publications/files/JDL-2004--fnl.pdf","raw_type":"text"},{"id":"pmh:doi:10.26180/20707477","is_oa":false,"landing_page_url":"https://monash.hosted.exlibrisgroup.com/permalink/f/31uhmh/catau21143513770001751","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Report"},{"id":"pmh:oai:figshare.com:article/20707477","is_oa":true,"landing_page_url":"https://figshare.com/articles/report/A_Hierarchical_Extraction_Policy_for_Content_Extraction_Signatures/20707477","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Report"},{"id":"doi:10.26180/20707477.v1","is_oa":true,"landing_page_url":"https://doi.org/10.26180/20707477.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407052105","display_name":"Monash University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Report"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20707477","is_oa":true,"landing_page_url":"https://figshare.com/articles/report/A_Hierarchical_Extraction_Policy_for_Content_Extraction_Signatures/20707477","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Report"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1497439563","https://openalex.org/W1526037005","https://openalex.org/W1566730292","https://openalex.org/W1589173790","https://openalex.org/W1594668186","https://openalex.org/W1614535124","https://openalex.org/W1642192185","https://openalex.org/W1653446932","https://openalex.org/W1794091104","https://openalex.org/W1950989567","https://openalex.org/W1978174042","https://openalex.org/W1996360405","https://openalex.org/W2046166587","https://openalex.org/W2072866771","https://openalex.org/W2080971756","https://openalex.org/W2095417143","https://openalex.org/W2096472369","https://openalex.org/W2156186849","https://openalex.org/W2506246362","https://openalex.org/W3022131440","https://openalex.org/W4232836212"],"related_works":["https://openalex.org/W2355730523","https://openalex.org/W152021879","https://openalex.org/W2149234266","https://openalex.org/W2390942931","https://openalex.org/W1932157736","https://openalex.org/W1981680180","https://openalex.org/W2033963098","https://openalex.org/W2125461068","https://openalex.org/W66604340","https://openalex.org/W2372753034"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
