{"id":"https://openalex.org/W2095104023","doi":"https://doi.org/10.1145/1731740.1731847","title":"Proposing of modular system for web information extraction","display_name":"Proposing of modular system for web information extraction","publication_year":2009,"publication_date":"2009-06-18","ids":{"openalex":"https://openalex.org/W2095104023","doi":"https://doi.org/10.1145/1731740.1731847","mag":"2095104023"},"language":"en","primary_location":{"id":"doi:10.1145/1731740.1731847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1731740.1731847","pdf_url":null,"source":{"id":"https://openalex.org/S4210222260","display_name":"Proceedings of the International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","issn_l":"1313-8936","issn":["1313-8936","1313-9037"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","raw_type":"proceedings-article"},"type":"article","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/A5031079938","display_name":"Vojt\u011bch Jirkovsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Vojt\u011bch Jirkovsk\u00fd","raw_affiliation_strings":["","Czech Technical University in Prague, Prague, Czechia"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Czech Technical University in Prague, Prague, Czechia","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070117038","display_name":"Ivan Jel\u00ednek","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ivan Jel\u00ednek","raw_affiliation_strings":["","Czech Technical University in Prague, Prague, Czechia"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Czech Technical University in Prague, Prague, Czechia","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031079938"],"corresponding_institution_ids":["https://openalex.org/I44504214"],"apc_list":null,"apc_paid":null,"fwci":1.3264,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83513248,"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":"1","last_page":"4"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9366999864578247,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9286999702453613,"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/automatism","display_name":"Automatism (medicine)","score":0.8305724859237671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726001739501953},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.7674378156661987},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6811837553977966},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.592896580696106},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5886196494102478},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5673859119415283},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5208576321601868},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4730512201786041},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3436402380466461},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32980096340179443},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11999961733818054},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08731627464294434}],"concepts":[{"id":"https://openalex.org/C2776614971","wikidata":"https://www.wikidata.org/wiki/Q2872623","display_name":"Automatism (medicine)","level":2,"score":0.8305724859237671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726001739501953},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.7674378156661987},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6811837553977966},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.592896580696106},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5886196494102478},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5673859119415283},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5208576321601868},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4730512201786041},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3436402380466461},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32980096340179443},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11999961733818054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08731627464294434},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C42219234","wikidata":"https://www.wikidata.org/wiki/Q131130","display_name":"Anesthesia","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1731740.1731847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1731740.1731847","pdf_url":null,"source":{"id":"https://openalex.org/S4210222260","display_name":"Proceedings of the International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","issn_l":"1313-8936","issn":["1313-8936","1313-9037"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1565395369","https://openalex.org/W1978799369","https://openalex.org/W2024623343","https://openalex.org/W2072936489","https://openalex.org/W2134150392"],"related_works":["https://openalex.org/W2001402863","https://openalex.org/W2170662188","https://openalex.org/W3094040214","https://openalex.org/W2416382811","https://openalex.org/W4236467370","https://openalex.org/W3135881914","https://openalex.org/W1553273561","https://openalex.org/W2350241213","https://openalex.org/W2270128259","https://openalex.org/W4287953066"],"abstract_inverted_index":{"The":[0],"paper":[1],"discusses":[2],"dimensions":[3],"and":[4,23,45,51],"parameters":[5],"of":[6,13,16],"web":[7],"information":[8],"extraction":[9,33],"such":[10],"as":[11],"level":[12],"automatism,":[14],"type":[15],"source":[17],"document":[18],"related":[19],"to":[20,39],"its":[21,43],"structuring":[22],"dependence":[24],"on":[25],"extractable":[26],"domain.":[27],"In":[28],"second":[29],"half":[30],"we":[31],"analyze":[32],"process":[34],"in":[35],"more":[36],"detail":[37],"according":[38],"considered":[40],"dimensions,":[41],"propose":[42],"phases":[44],"discuss":[46],"modules":[47],"for":[48],"each":[49],"one":[50],"interfaces":[52],"between":[53],"phases.":[54]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
