{"id":"https://openalex.org/W2113360486","doi":"https://doi.org/10.1109/iat.2003.1241057","title":"Learning knowledge bases for information extraction from multiple text based Web sites","display_name":"Learning knowledge bases for information extraction from multiple text based Web sites","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2113360486","doi":"https://doi.org/10.1109/iat.2003.1241057","mag":"2113360486"},"language":"en","primary_location":{"id":"doi:10.1109/iat.2003.1241057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2003.1241057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.","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/A5068382420","display_name":"Xiaoying Gao","orcid":"https://orcid.org/0000-0002-6326-7947"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Xiaoying Gao","raw_affiliation_strings":["School of Mathematical and Computing Sciences, Victoria University of Wellington, New Zealand","Sch. of Math. & Comput. Sci., Victoria Univ. of Wellington, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computing Sciences, Victoria University of Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]},{"raw_affiliation_string":"Sch. of Math. & Comput. Sci., Victoria Univ. of Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mengjie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Mengjie Zhang","raw_affiliation_strings":["School of Mathematical and Computing Sciences, Victoria University of Wellington, New Zealand","Sch. of Math. & Comput. Sci., Victoria Univ. of Wellington, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Computing Sciences, Victoria University of Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]},{"raw_affiliation_string":"Sch. of Math. & Comput. Sci., Victoria Univ. of Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41156924"],"apc_list":null,"apc_paid":null,"fwci":0.4311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59668818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9824000000953674,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9707000255584717,"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":0.8214537501335144},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.6695564389228821},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6689376831054688},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.650607705116272},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.6129230260848999},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6048206686973572},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6015505790710449},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5887231230735779},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.570648193359375},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5687987804412842},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.5643160939216614},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.46435192227363586},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4639771580696106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42509031295776367},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3577015995979309},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2722074091434479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214537501335144},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.6695564389228821},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6689376831054688},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.650607705116272},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.6129230260848999},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6048206686973572},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6015505790710449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5887231230735779},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.570648193359375},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5687987804412842},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.5643160939216614},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.46435192227363586},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4639771580696106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42509031295776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3577015995979309},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2722074091434479},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iat.2003.1241057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2003.1241057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1487227972","https://openalex.org/W1556829891","https://openalex.org/W1968067123","https://openalex.org/W2001131973","https://openalex.org/W2026080185","https://openalex.org/W2059564455","https://openalex.org/W2081580037","https://openalex.org/W2131165428","https://openalex.org/W2135479443","https://openalex.org/W2136500370","https://openalex.org/W2140327372","https://openalex.org/W2163126391","https://openalex.org/W2164949130","https://openalex.org/W3006373977","https://openalex.org/W4285719527","https://openalex.org/W6629070510","https://openalex.org/W6633086566"],"related_works":["https://openalex.org/W1520100787","https://openalex.org/W2357854711","https://openalex.org/W2904591968","https://openalex.org/W1838463810","https://openalex.org/W3045387744","https://openalex.org/W1550883778","https://openalex.org/W2793744252","https://openalex.org/W2126191795","https://openalex.org/W248531889","https://openalex.org/W2294170235"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,57],"learning":[3,35,116],"approach":[4,76],"to":[5,25,39],"automatically":[6,40,55],"building":[7],"knowledge":[8,28,30,42,109,122,134],"bases":[9],"for":[10,139],"information":[11,94,140],"extraction":[12,141],"from":[13,45,127,142],"multiple":[14,149],"text":[15],"based":[16,21],"Web":[17,61,81,146,150],"pages.":[18],"A":[19,33],"frame":[20,34,111,115],"representation":[22,112],"is":[23,37],"introduced":[24],"represent":[26],"domain":[27,120,132],"as":[29],"unit":[31,43,110],"frames.":[32],"algorithm":[36,117],"developed":[38],"learn":[41],"frames":[44],"training":[46,49,128],"examples.":[47],"Some":[48],"examples":[50],"can":[51,124,136],"be":[52,125,137],"obtained":[53],"by":[54],"parsing":[56],"number":[58],"of":[59,83],"tabular":[60],"pages":[62,147],"in":[63],"the":[64,70,93,108,114,131],"same":[65],"domain,":[66],"which":[67],"greatly":[68],"reduced":[69],"time":[71],"consuming":[72],"manual":[73],"work.":[74],"This":[75],"was":[77,95],"investigated":[78],"on":[79,148],"ten":[80],"sites":[82],"real":[84],"estate":[85],"advertisements":[86,89],"and":[87,90,113,130],"car":[88],"nearly":[91],"all":[92],"successfully":[96],"extracted":[97],"with":[98],"very":[99],"few":[100],"false":[101],"alarms.":[102],"These":[103],"results":[104],"suggest":[105],"that":[106],"both":[107],"work":[118],"well,":[119],"specific":[121,133],"base":[123,135],"learned":[126],"examples,":[129],"used":[138],"flexible":[143],"text-based":[144],"semi-structured":[145],"sites.":[151]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
