{"id":"https://openalex.org/W2157968177","doi":"https://doi.org/10.1109/saintw.2003.1210172","title":"Information extraction from HTML pages and its integration","display_name":"Information extraction from HTML pages and its integration","publication_year":2003,"publication_date":"2003-08-27","ids":{"openalex":"https://openalex.org/W2157968177","doi":"https://doi.org/10.1109/saintw.2003.1210172","mag":"2157968177"},"language":"en","primary_location":{"id":"doi:10.1109/saintw.2003.1210172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saintw.2003.1210172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 Symposium on Applications and the Internet Workshops, 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/A5014204198","display_name":"K. Itai","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Itai","raw_affiliation_strings":["University of Tokyo, Chiyoda, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Chiyoda, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087434029","display_name":"Atsuhiro Takasu","orcid":"https://orcid.org/0000-0002-9061-7949"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"A. Takasu","raw_affiliation_strings":["National Institute of Information, Chiyoda, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information, Chiyoda, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102957694","display_name":"Jun Adachi","orcid":"https://orcid.org/0000-0001-5553-0402"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"J. Adachi","raw_affiliation_strings":["National Institute of Information, Chiyoda, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information, Chiyoda, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7567,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72824265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"276","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9955000281333923,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9876000285148621,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8178930282592773},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7107253670692444},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6837561130523682},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6482291221618652},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6389412879943848},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6368168592453003},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5252858400344849},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5238430500030518},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5093387365341187},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.4563924968242645},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4544248878955841},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.44581133127212524},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.41613033413887024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36429354548454285},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3579874038696289},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1666434407234192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178930282592773},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7107253670692444},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6837561130523682},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6482291221618652},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6389412879943848},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6368168592453003},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5252858400344849},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5238430500030518},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5093387365341187},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.4563924968242645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4544248878955841},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.44581133127212524},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.41613033413887024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36429354548454285},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3579874038696289},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1666434407234192},{"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/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/saintw.2003.1210172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saintw.2003.1210172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 Symposium on Applications and the Internet Workshops, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W25291738","https://openalex.org/W1574862351","https://openalex.org/W2023673418","https://openalex.org/W2145948275","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W6601003611","https://openalex.org/W6634328381","https://openalex.org/W6682304300"],"related_works":["https://openalex.org/W36911888","https://openalex.org/W4385731361","https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W2373402338","https://openalex.org/W2114620981","https://openalex.org/W4302086745","https://openalex.org/W2359623206","https://openalex.org/W2626998250","https://openalex.org/W2411679502"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,13,62,74,86],"method":[3],"for":[4],"transforming":[5],"HTML":[6,33],"tables":[7,46],"that":[8],"have":[9],"different":[10],"structures":[11],"into":[12],"common":[14],"XML":[15],"list":[16],"structure":[17,68],"and":[18,27,47,70,78,90],"integrating":[19],"them.":[20],"This":[21,36],"integration":[22],"enables":[23],"us":[24],"to":[25],"browse":[26],"compare":[28,55],"all":[29],"information":[30,43],"in":[31],"separate":[32],"pages":[34],"uniformly.":[35],"paper":[37],"focuses":[38],"on":[39],"the":[40,83,97],"tasks":[41],"of":[42,85],"extraction":[44],"from":[45],"its":[48],"data":[49,59,71,80],"categorization.":[50],"For":[51],"this":[52],"purpose,":[53],"we":[54,95],"three":[56],"algorithms:":[57],"(I)":[58],"classification":[60,81],"using":[61,73],"support":[63,87],"vector":[64,88],"machine,":[65],"(II)":[66],"table":[67],"estimation":[69],"categorization":[72],"hidden":[75,91],"Markov":[76,92],"model,":[77],"(III)":[79],"by":[82],"combination":[84],"machine":[89],"model.":[93],"Finally,":[94],"report":[96],"experimental":[98],"results.":[99]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
