{"id":"https://openalex.org/W146288251","doi":"https://doi.org/10.1007/978-3-642-24396-7_6","title":"Automatic Extraction Rules Generation Based on XPath Pattern Learning","display_name":"Automatic Extraction Rules Generation Based on XPath Pattern Learning","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W146288251","doi":"https://doi.org/10.1007/978-3-642-24396-7_6","mag":"146288251"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-24396-7_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-24396-7_6","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/A5100434273","display_name":"Jingwei Zhang","orcid":"https://orcid.org/0000-0002-7907-2853"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingwei Zhang","raw_affiliation_strings":["Institute of Massive Computing, East China Normal University, Shanghai, 200062, China"],"affiliations":[{"raw_affiliation_string":"Institute of Massive Computing, East China Normal University, Shanghai, 200062, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440825","display_name":"Can Zhang","orcid":"https://orcid.org/0000-0001-8127-9282"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Zhang","raw_affiliation_strings":["Institute of Massive Computing, East China Normal University, Shanghai, 200062, China"],"affiliations":[{"raw_affiliation_string":"Institute of Massive Computing, East China Normal University, Shanghai, 200062, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089931216","display_name":"Weining Qian","orcid":"https://orcid.org/0000-0002-4132-8630"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weining Qian","raw_affiliation_strings":["Institute of Massive Computing, East China Normal University, Shanghai, 200062, China"],"affiliations":[{"raw_affiliation_string":"Institute of Massive Computing, East China Normal University, Shanghai, 200062, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101511862","display_name":"Aoying Zhou","orcid":"https://orcid.org/0000-0002-4665-7302"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoying Zhou","raw_affiliation_strings":["Institute of Massive Computing, East China Normal University, Shanghai, 200062, China"],"affiliations":[{"raw_affiliation_string":"Institute of Massive Computing, East China Normal University, Shanghai, 200062, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100434273"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.2061,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87868884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"69"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9751999974250793,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9750999808311462,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.956663966178894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8675466775894165},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5893383622169495},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.572008490562439},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5657029151916504},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4748906195163727},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4462677538394928},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44616830348968506},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.44279319047927856},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4350551664829254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.326265811920166},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.2809258699417114},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07557812333106995}],"concepts":[{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.956663966178894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675466775894165},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5893383622169495},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.572008490562439},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5657029151916504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4748906195163727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4462677538394928},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44616830348968506},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.44279319047927856},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4350551664829254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.326265811920166},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2809258699417114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07557812333106995},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","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/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-24396-7_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-24396-7_6","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1567298333","https://openalex.org/W1602270052","https://openalex.org/W1616576116","https://openalex.org/W1679624670","https://openalex.org/W1826831057","https://openalex.org/W2049675797","https://openalex.org/W2070046067","https://openalex.org/W2104086170","https://openalex.org/W2105803339","https://openalex.org/W2116493296","https://openalex.org/W2143197360","https://openalex.org/W2144416276","https://openalex.org/W2145066849","https://openalex.org/W2148210463","https://openalex.org/W2252034896","https://openalex.org/W2915063781","https://openalex.org/W4301113013"],"related_works":["https://openalex.org/W1542110834","https://openalex.org/W2611888112","https://openalex.org/W2121120069","https://openalex.org/W562932586","https://openalex.org/W2124793519","https://openalex.org/W1525800142","https://openalex.org/W2398280235","https://openalex.org/W2367919820","https://openalex.org/W4385731361","https://openalex.org/W4280620143"],"abstract_inverted_index":null,"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
