{"id":"https://openalex.org/W1795600436","doi":"https://doi.org/10.1007/978-3-540-87479-9_31","title":"Bootstrapping Information Extraction from Semi-structured Web Pages","display_name":"Bootstrapping Information Extraction from Semi-structured Web Pages","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W1795600436","doi":"https://doi.org/10.1007/978-3-540-87479-9_31","mag":"1795600436"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-87479-9_31","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-87479-9_31","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","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/A5101513166","display_name":"J. Andrew Carlson","orcid":"https://orcid.org/0000-0002-6866-6314"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Carlson","raw_affiliation_strings":["Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA","Machine Learning Department, Carnegie Mellon University, Pittsburgh, USA PA 15213#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University, Pittsburgh, USA PA 15213#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070221595","display_name":"Charles Schafer","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Schafer","raw_affiliation_strings":["Google, Inc., 4720 Forbes Avenue, Pittsburgh, PA 15213, USA","Google, Inc., Pittsburgh, USA PA 15213"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., 4720 Forbes Avenue, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., Pittsburgh, USA PA 15213","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":4.2213,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95224057,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"210"},"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":0.9617000222206116,"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/T11478","display_name":"Caching and Content Delivery","score":0.9562000036239624,"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":0.8245493173599243},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5620467066764832},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5544808506965637},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5488763451576233},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5387199521064758},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46692726016044617},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4596706032752991},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4495314061641693},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4453080892562866},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3805932402610779},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3534260392189026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2742169499397278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245493173599243},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5620467066764832},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5544808506965637},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5488763451576233},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5387199521064758},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46692726016044617},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4596706032752991},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4495314061641693},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4453080892562866},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3805932402610779},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3534260392189026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2742169499397278},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-540-87479-9_31","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-87479-9_31","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.2991","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.2991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~acarlson/papers/carlson-ecml08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1511374591","https://openalex.org/W1553019137","https://openalex.org/W1563062065","https://openalex.org/W1645816215","https://openalex.org/W1950165262","https://openalex.org/W2008214196","https://openalex.org/W2015551056","https://openalex.org/W2043440779","https://openalex.org/W2069388662","https://openalex.org/W2071628657","https://openalex.org/W2108267498","https://openalex.org/W2120084270","https://openalex.org/W2143309843","https://openalex.org/W2153072229","https://openalex.org/W2160196229","https://openalex.org/W2162340487","https://openalex.org/W3100344990","https://openalex.org/W4232071090","https://openalex.org/W4232438669"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W2361861616","https://openalex.org/W156620619","https://openalex.org/W2098233217","https://openalex.org/W2914363205","https://openalex.org/W2616249226","https://openalex.org/W2997844990","https://openalex.org/W4387366173","https://openalex.org/W36911888"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
