{"id":"https://openalex.org/W1504930927","doi":"https://doi.org/10.1007/978-0-387-39940-9_459","title":"Web Information Extraction","display_name":"Web Information Extraction","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1504930927","doi":"https://doi.org/10.1007/978-0-387-39940-9_459","mag":"1504930927"},"language":"en","primary_location":{"id":"doi:10.1007/978-0-387-39940-9_459","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-0-387-39940-9_459","pdf_url":null,"source":{"id":"https://openalex.org/S4306509343","display_name":"Encyclopedia of Database Systems","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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Database Systems","raw_type":"book-chapter"},"type":"reference-entry","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/A5102820528","display_name":"Rajasekar Krishnamurthy","orcid":"https://orcid.org/0000-0002-1245-4152"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajasekar Krishnamurthy","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404797","display_name":"Yunyao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyao Li","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113793867","display_name":"Sriram Raghavan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Raghavan","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074416632","display_name":"Frederick Reiss","orcid":"https://orcid.org/0009-0002-1254-1798"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frederick Reiss","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010223683","display_name":"Shivakumar Vaithyanathan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivakumar Vaithyanathan","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076801334","display_name":"Huaiyu Zhu","orcid":"https://orcid.org/0000-0001-6918-4088"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaiyu Zhu","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3473","last_page":"3478"},"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/T11719","display_name":"Data Quality and Management","score":0.9763000011444092,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9491999745368958,"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":0.5374183654785156},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.532371461391449},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4886170029640198},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46608346700668335},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43958571553230286},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3356287479400635},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0966251790523529},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.09642988443374634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5374183654785156},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.532371461391449},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4886170029640198},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46608346700668335},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43958571553230286},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3356287479400635},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0966251790523529},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.09642988443374634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-0-387-39940-9_459","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-0-387-39940-9_459","pdf_url":null,"source":{"id":"https://openalex.org/S4306509343","display_name":"Encyclopedia of Database Systems","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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Encyclopedia of Database Systems","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W10455613","https://openalex.org/W1998969485","https://openalex.org/W2022760666","https://openalex.org/W2035266017","https://openalex.org/W2068882115","https://openalex.org/W2154148563","https://openalex.org/W2154531419","https://openalex.org/W2159491434","https://openalex.org/W4231867741"],"related_works":["https://openalex.org/W1788528807","https://openalex.org/W1975174578","https://openalex.org/W104581431","https://openalex.org/W2725657302","https://openalex.org/W1561729373","https://openalex.org/W2393978999","https://openalex.org/W1548492051","https://openalex.org/W2153799433","https://openalex.org/W1963586751","https://openalex.org/W2726507998"],"abstract_inverted_index":null,"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}