{"id":"https://openalex.org/W2112546875","doi":"https://doi.org/10.1109/wise.2002.1181667","title":"Data-rich section extraction from HTML pages","display_name":"Data-rich section extraction from HTML pages","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2112546875","doi":"https://doi.org/10.1109/wise.2002.1181667","mag":"2112546875"},"language":"en","primary_location":{"id":"doi:10.1109/wise.2002.1181667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wise.2002.1181667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Conference on Web Information Systems Engineering, 2002. WISE 2002.","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/A5101772320","display_name":"Jiying Wang","orcid":"https://orcid.org/0009-0007-5487-8643"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiying Wang","raw_affiliation_strings":["Department of Computer Science, University of Science and Technology, Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Science and Technology, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071759146","display_name":"Frederick H. Lochovsky","orcid":"https://orcid.org/0000-0001-7470-4172"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"F.H. Lochovsky","raw_affiliation_strings":["Department of Computer Science, University of Science and Technology, Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Science and Technology, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.4091,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.97769526,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"322"},"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":0.9902999997138977,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9789000153541565,"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":0.7996992468833923},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7609500288963318},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6122392416000366},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6061246395111084},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5956841111183167},{"id":"https://openalex.org/keywords/section","display_name":"Section (typography)","score":0.5773506164550781},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5699756145477295},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5501464605331421},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5455921292304993},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.43777352571487427},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18297478556632996},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05801549553871155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996992468833923},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7609500288963318},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6122392416000366},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6061246395111084},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5956841111183167},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.5773506164550781},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5699756145477295},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5501464605331421},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5455921292304993},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.43777352571487427},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18297478556632996},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05801549553871155},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wise.2002.1181667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wise.2002.1181667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third International Conference on Web Information Systems Engineering, 2002. WISE 2002.","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-38122","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-38122","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1854214752","https://openalex.org/W1981202432","https://openalex.org/W2005124845","https://openalex.org/W2006119904","https://openalex.org/W2020423193","https://openalex.org/W2066636486","https://openalex.org/W2079672501","https://openalex.org/W2100815879","https://openalex.org/W2124436456","https://openalex.org/W2124673015","https://openalex.org/W2128836931","https://openalex.org/W2156632103","https://openalex.org/W2160196229","https://openalex.org/W2166407869","https://openalex.org/W2169337167","https://openalex.org/W4233527139","https://openalex.org/W4240407914","https://openalex.org/W6639055396","https://openalex.org/W6678701036","https://openalex.org/W6683392976"],"related_works":["https://openalex.org/W36911888","https://openalex.org/W4385731361","https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W4302086745","https://openalex.org/W2373402338","https://openalex.org/W2114620981","https://openalex.org/W2626998250","https://openalex.org/W2184959150","https://openalex.org/W2154146989"],"abstract_inverted_index":{"We":[0,20],"propose":[1],"a":[2,26,122],"novel":[3],"algorithm,":[4,103,114],"DSE":[5,23,54],"(data-rich":[6],"subtree":[7],"extraction)":[8],"to":[9,94,120],"recognize":[10],"and":[11,39,85],"extract":[12],"the":[13,22,48,53,72,77,83,88,95,101,107],"data-rich":[14,59],"section":[15],"of":[16,61,87,109],"an":[17],"HTML":[18,62,125],"page.":[19],"apply":[21],"algorithm":[24,55],"as":[25],"pre-processing":[27],"\"clean-up\"":[28],"step":[29],"for":[30,47,76,124],"two":[31],"typical":[32],"Web":[33,40,96],"information":[34,41,97],"retrieval":[35],"problems:":[36],"topic":[37,78],"distillation":[38,79],"extraction.":[42],"Our":[43],"experiments":[44],"show":[45],"that,":[46],"test":[49],"data":[50],"sets":[51],"used,":[52],"can":[56,69,105],"correctly":[57],"identify":[58],"sections":[60],"pages":[63],"with":[64],"100%":[65],"accuracy.":[66],"Therefore,":[67],"it":[68,104],"effectively":[70],"reduce":[71],"root":[73],"set":[74],"size":[75],"problem":[80,99],"thereby":[81],"improving":[82],"precision":[84],"accuracy":[86],"IETS":[89],"algorithm.":[90],"Furthermore,":[91],"when":[92],"applied":[93],"extraction":[98],"using":[100],"IEPAD":[102],"decrease":[106],"number":[108],"patterns":[110],"discovered":[111],"by":[112],"this":[113],"thus":[115],"shortening":[116],"its":[117],"time":[118],"cost":[119],"generalize":[121],"wrapper":[123],"pages.":[126]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
