{"id":"https://openalex.org/W2465169987","doi":"https://doi.org/10.1007/978-3-319-31750-2_38","title":"Efficient Page-Level Data Extraction via Schema Induction and Verification","display_name":"Efficient Page-Level Data Extraction via Schema Induction and Verification","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2465169987","doi":"https://doi.org/10.1007/978-3-319-31750-2_38","mag":"2465169987"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-31750-2_38","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-31750-2_38","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/A5078524542","display_name":"Chia\u2010Hui Chang","orcid":"https://orcid.org/0000-0002-1101-6337"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chia-Hui Chang","raw_affiliation_strings":["CSIE, National Central University, Zhongli District, Taiwan"],"affiliations":[{"raw_affiliation_string":"CSIE, National Central University, Zhongli District, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102001605","display_name":"Tiansheng Chen","orcid":"https://orcid.org/0000-0001-8520-7622"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tian-Sheng Chen","raw_affiliation_strings":["CSIE, National Central University, Zhongli District, Taiwan"],"affiliations":[{"raw_affiliation_string":"CSIE, National Central University, Zhongli District, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038343888","display_name":"Ming-Chuan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Chuan Chen","raw_affiliation_strings":["CSIE, National Central University, Zhongli District, Taiwan"],"affiliations":[{"raw_affiliation_string":"CSIE, National Central University, Zhongli District, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082612031","display_name":"Jhung-Li Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jhung-Li Ding","raw_affiliation_strings":["CSIE, National Central University, Zhongli District, Taiwan"],"affiliations":[{"raw_affiliation_string":"CSIE, National Central University, Zhongli District, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078524542"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.626,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89771677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"478","last_page":"490"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9750000238418579,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9731000065803528,"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":0.8942670822143555},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7756375074386597},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7659242153167725},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4884609282016754},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4753134846687317},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4713781774044037},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4675979018211365},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.43174540996551514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3345627188682556},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2245144248008728},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18305563926696777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8942670822143555},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7756375074386597},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7659242153167725},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4884609282016754},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4753134846687317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4713781774044037},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4675979018211365},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.43174540996551514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3345627188682556},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2245144248008728},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18305563926696777},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-31750-2_38","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-31750-2_38","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1999361961","https://openalex.org/W2005646337","https://openalex.org/W2024091454","https://openalex.org/W2040757233","https://openalex.org/W2085016361","https://openalex.org/W2104086170","https://openalex.org/W2115770258","https://openalex.org/W2121751007","https://openalex.org/W2134150392","https://openalex.org/W2142385501","https://openalex.org/W2150721933","https://openalex.org/W2160189941","https://openalex.org/W2171364811","https://openalex.org/W2912161846","https://openalex.org/W4206550178"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
