{"id":"https://openalex.org/W77038413","doi":"https://doi.org/10.1007/978-3-319-12024-9_11","title":"A Template-Based Information Extraction from Web Sites with Unstable Markup","display_name":"A Template-Based Information Extraction from Web Sites with Unstable Markup","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W77038413","doi":"https://doi.org/10.1007/978-3-319-12024-9_11","mag":"77038413"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-12024-9_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-12024-9_11","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information 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/A5018430083","display_name":"Maxim Kolchin","orcid":"https://orcid.org/0000-0002-3851-9874"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Maxim Kolchin","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038679205","display_name":"Fedor Kozlov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Fedor Kozlov","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018430083"],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":6.3197,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9667859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9932000041007996,"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/markup-language","display_name":"Markup language","score":0.886359453201294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6672435998916626},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6141363978385925},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.559813916683197},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.495051771402359},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4915941655635834},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.45933523774147034},{"id":"https://openalex.org/keywords/sgml","display_name":"SGML","score":0.4299926161766052},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.25846344232559204},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1852198839187622},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.1844070851802826},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1651633381843567},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.07025203108787537}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.886359453201294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672435998916626},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6141363978385925},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.559813916683197},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.495051771402359},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4915941655635834},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.45933523774147034},{"id":"https://openalex.org/C62701983","wikidata":"https://www.wikidata.org/wiki/Q207819","display_name":"SGML","level":4,"score":0.4299926161766052},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.25846344232559204},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1852198839187622},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.1844070851802826},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1651633381843567},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.07025203108787537}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-12024-9_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-12024-9_11","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W1552847225"],"related_works":["https://openalex.org/W2044641582","https://openalex.org/W2186877208","https://openalex.org/W2084734328","https://openalex.org/W4232022739","https://openalex.org/W2076638146","https://openalex.org/W2060814800","https://openalex.org/W2768131452","https://openalex.org/W2099020626","https://openalex.org/W12825674","https://openalex.org/W2101294324"],"abstract_inverted_index":null,"counts_by_year":[{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
