{"id":"https://openalex.org/W1993035437","doi":"https://doi.org/10.1145/1806338.1806426","title":"Information extraction from web tables","display_name":"Information extraction from web tables","publication_year":2009,"publication_date":"2009-12-14","ids":{"openalex":"https://openalex.org/W1993035437","doi":"https://doi.org/10.1145/1806338.1806426","mag":"1993035437"},"language":"en","primary_location":{"id":"doi:10.1145/1806338.1806426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1806338.1806426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Information Integration and Web-based Applications & Services","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/A5013795150","display_name":"Mahmoud Shaker","orcid":"https://orcid.org/0000-0002-9501-1014"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mahmoud Shaker","raw_affiliation_strings":["Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000398352","display_name":"Hamidah Ibrahim","orcid":"https://orcid.org/0000-0002-9900-0531"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Hamidah Ibrahim","raw_affiliation_strings":["Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032045434","display_name":"Aida Mustapha","orcid":"https://orcid.org/0000-0002-9077-4995"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Aida Mustapha","raw_affiliation_strings":["Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019058734","display_name":"Lili Nurliyana Abdullah","orcid":"https://orcid.org/0000-0001-8704-2390"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lili Nurliyana Abdullah","raw_affiliation_strings":["Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130343225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"470","last_page":"476"},"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/T11719","display_name":"Data Quality and Management","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8169423937797546},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7571924328804016},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6299553513526917},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6178164482116699},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5764188170433044},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5561764240264893},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5343524217605591},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4724239110946655},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.4702267348766327},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4363982677459717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169423937797546},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7571924328804016},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6299553513526917},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6178164482116699},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5764188170433044},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5561764240264893},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5343524217605591},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4724239110946655},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.4702267348766327},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4363982677459717}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1806338.1806426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1806338.1806426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Conference on Information Integration and Web-based Applications & Services","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":17,"referenced_works":["https://openalex.org/W180206698","https://openalex.org/W1553137647","https://openalex.org/W1822702654","https://openalex.org/W1988217119","https://openalex.org/W2005970231","https://openalex.org/W2008272135","https://openalex.org/W2015415022","https://openalex.org/W2046817824","https://openalex.org/W2078206655","https://openalex.org/W2102189859","https://openalex.org/W2102966069","https://openalex.org/W2104086170","https://openalex.org/W2108770713","https://openalex.org/W2158168860","https://openalex.org/W2159240506","https://openalex.org/W2160196229","https://openalex.org/W4231818376"],"related_works":["https://openalex.org/W2404573736","https://openalex.org/W4205141839","https://openalex.org/W2021161024","https://openalex.org/W2941499861","https://openalex.org/W2117924798","https://openalex.org/W1981112637","https://openalex.org/W2057820341","https://openalex.org/W2116470944","https://openalex.org/W2184266942","https://openalex.org/W151257976"],"abstract_inverted_index":{"Nowadays,":[0],"many":[1],"users":[2,33],"use":[3],"web":[4,19,83,97,113,122,135,171],"search":[5,41],"engines":[6],"to":[7,32,48,107,179],"find":[8],"and":[9,28,46,92,109,156,193],"gather":[10],"information.":[11],"User":[12],"faces":[13],"an":[14,129],"increasing":[15,93],"amount":[16,94],"of":[17,25,62,95,112,118,145,170,182],"various":[18],"pages":[20,71,84,98,114,172],"information":[21,31,58,68,76,80,99,119,133],"sources.":[22],"The":[23,141,159],"issue":[24],"correlating,":[26],"integrating":[27],"presenting":[29],"related":[30],"becomes":[34,86],"important.":[35],"When":[36],"a":[37,40,50,123,168],"user":[38],"uses":[39],"engine":[42],"such":[43],"as":[44,178],"Yahoo":[45],"Google":[47],"seek":[49],"specific":[51],"information,":[52,65],"the":[53,60,63,74,82,90,102,110,116,174,180,187],"results":[54],"are":[55,105],"not":[56],"only":[57,188],"about":[59,69],"availability":[61],"desired":[64,75],"but":[66],"also":[67,85],"other":[70],"on":[72,138,167],"which":[73],"is":[77,162,186],"mentioned.":[78],"Extracting":[79],"from":[81,121,134,173],"very":[87],"important":[88],"because":[89],"massive":[91],"diverse":[96],"sources":[100],"in":[101],"Internet":[103],"that":[104,190],"available":[106],"users,":[108],"variety":[111],"making":[115],"process":[117],"extraction":[120],"challenging":[124],"problem.":[125],"This":[126],"paper":[127],"proposes":[128],"approach":[130,143,161],"for":[131],"extracting":[132],"tables":[136],"based":[137],"standard":[139,195],"classifications.":[140],"proposed":[142,160],"consists":[144],"four":[146],"main":[147],"phases,":[148],"namely:":[149],"(i)":[150],"pre-processing,":[151],"(ii)":[152],"extraction,":[153],"(iii)":[154],"classification,":[155],"(iv)":[157],"simplification.":[158],"evaluated":[163],"by":[164],"conducting":[165],"experiments":[166],"number":[169],"Nokia":[175],"products":[176],"domain,":[177],"best":[181],"our":[183],"knowledge":[184],"this":[185],"product":[189],"has":[191],"complete":[192],"complex":[194],"classifiers.":[196]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}