{"id":"https://openalex.org/W4229955244","doi":"https://doi.org/10.1007/978-1-4614-8265-9_459","title":"Web Information Extraction","display_name":"Web Information Extraction","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W4229955244","doi":"https://doi.org/10.1007/978-1-4614-8265-9_459"},"language":"en","primary_location":{"id":"doi:10.1007/978-1-4614-8265-9_459","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-1-4614-8265-9_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":"book-chapter","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/A5050310059","display_name":"Laura Chiticariu","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":true,"raw_author_name":"Laura Chiticariu","raw_affiliation_strings":["Scalable Natural Language Processing, IBM Research \u2013 Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Scalable Natural Language Processing, IBM Research \u2013 Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048281388","display_name":"Marina Danilevsky","orcid":"https://orcid.org/0000-0003-2875-2442"},"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":"Marina Danilevsky","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004469222","display_name":"Howard Ho","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":"Howard Ho","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","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, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102944075","display_name":"Yunyao Li","orcid":"https://orcid.org/0009-0002-0814-4634"},"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, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, 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, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, 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, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, 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, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, 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, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5050310059"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":0.441,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68582375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4620","last_page":"4629"},"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":0.9847999811172485,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9628000259399414,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4991331100463867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4850010573863983},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46714043617248535},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.430271714925766},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40977704524993896},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08663696050643921},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08354029059410095}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4991331100463867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4850010573863983},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46714043617248535},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.430271714925766},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40977704524993896},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08663696050643921},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08354029059410095}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-1-4614-8265-9_459","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-1-4614-8265-9_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":[{"display_name":"Decent work and economic growth","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W10455613","https://openalex.org/W55204438","https://openalex.org/W74439177","https://openalex.org/W85648037","https://openalex.org/W89279510","https://openalex.org/W1502957213","https://openalex.org/W1536741282","https://openalex.org/W1583837637","https://openalex.org/W1602136775","https://openalex.org/W1987562803","https://openalex.org/W1988148447","https://openalex.org/W1998969485","https://openalex.org/W1999563429","https://openalex.org/W2022760666","https://openalex.org/W2035266017","https://openalex.org/W2038941723","https://openalex.org/W2068882115","https://openalex.org/W2106950427","https://openalex.org/W2108475322","https://openalex.org/W2114998795","https://openalex.org/W2152431819","https://openalex.org/W2154148563","https://openalex.org/W2154531419","https://openalex.org/W2162829716","https://openalex.org/W2166709576","https://openalex.org/W4231867741"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}