{"id":"https://openalex.org/W2058591921","doi":"https://doi.org/10.1145/2539150.2539170","title":"Strigil","display_name":"Strigil","publication_year":2013,"publication_date":"2013-12-02","ids":{"openalex":"https://openalex.org/W2058591921","doi":"https://doi.org/10.1145/2539150.2539170","mag":"2058591921"},"language":"en","primary_location":{"id":"doi:10.1145/2539150.2539170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2539150.2539170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of International Conference on Information Integration and Web-based Applications &amp; Services","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/A5025401928","display_name":"Jakub St\u00e1rka","orcid":null},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jakub St\u00e1rka","raw_affiliation_strings":["Department of Software Engineering, Charles University in Prague, Czech Republic","Department of Software Engineering, Charles University in Prague, Czech Republic#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Charles University in Prague, Czech Republic","institution_ids":["https://openalex.org/I21250087"]},{"raw_affiliation_string":"Department of Software Engineering, Charles University in Prague, Czech Republic#TAB#","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061978151","display_name":"Irena Holubov\u00e1","orcid":"https://orcid.org/0000-0003-2113-1539"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Irena Holubov\u00e1","raw_affiliation_strings":["Department of Software Engineering, Charles University in Prague, Czech Republic","Department of Software Engineering, Charles University in Prague, Czech Republic#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Charles University in Prague, Czech Republic","institution_ids":["https://openalex.org/I21250087"]},{"raw_affiliation_string":"Department of Software Engineering, Charles University in Prague, Czech Republic#TAB#","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091643071","display_name":"Martin Ne\u010dask\u00fd","orcid":"https://orcid.org/0000-0002-5186-7734"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Ne\u010dask\u00fd","raw_affiliation_strings":["Department of Software Engineering, Charles University in Prague, Czech Republic","Department of Software Engineering, Charles University in Prague, Czech Republic#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Charles University in Prague, Czech Republic","institution_ids":["https://openalex.org/I21250087"]},{"raw_affiliation_string":"Department of Software Engineering, Charles University in Prague, Czech Republic#TAB#","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025401928"],"corresponding_institution_ids":["https://openalex.org/I21250087"],"apc_list":null,"apc_paid":null,"fwci":0.8089,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82490044,"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":"453","last_page":"462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9940999746322632,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8613264560699463},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5644673109054565},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5566055178642273},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5371896028518677},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44164761900901794},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42517560720443726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613264560699463},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5644673109054565},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5566055178642273},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5371896028518677},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44164761900901794},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42517560720443726},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2539150.2539170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2539150.2539170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W125960106","https://openalex.org/W1968053850","https://openalex.org/W2035302703","https://openalex.org/W2062543449","https://openalex.org/W2083413555","https://openalex.org/W2108223890","https://openalex.org/W2114541504","https://openalex.org/W2118165382","https://openalex.org/W4240555197","https://openalex.org/W4245444791"],"related_works":["https://openalex.org/W2003333417","https://openalex.org/W2378862226","https://openalex.org/W118236634","https://openalex.org/W2355326633","https://openalex.org/W2804669904","https://openalex.org/W2149777447","https://openalex.org/W2347456287","https://openalex.org/W2121651557","https://openalex.org/W2782969047","https://openalex.org/W4401210459"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2,31],"we":[3,43],"introduce":[4],"Strigil,":[5],"a":[6,23,45,81,85],"framework":[7,36],"for":[8],"automated":[9],"data":[10,24,56,73,86,111],"extraction.":[11],"It":[12],"represents":[13],"an":[14,106],"easily":[15],"configurable":[16],"tool":[17],"that":[18],"enables":[19],"one":[20],"to":[21,54,80,103,108,113],"retrieve":[22],"from":[25,57],"textual":[26],"or":[27,84],"weak-structured":[28],"documents.":[29,61],"The":[30],"contains":[32],"description":[33],"of":[34,60,72],"the":[35,50],"architecture":[37],"and":[38,92,96,115],"its":[39],"important":[40],"components.":[41],"Additionally,":[42],"propose":[44],"scraping":[46,99],"language":[47,100],"inspired":[48],"by":[49],"XSL":[51],"transformations":[52],"designed":[53,102],"extract":[55],"different":[58,66],"kinds":[59],"Although":[62],"there":[63],"are":[64,76],"many":[65],"approaches":[67],"focused":[68],"on":[69],"various":[70],"aspects":[71],"scraping,":[74],"they":[75],"usually":[77],"very":[78],"specialized":[79],"concrete":[82],"domain":[83],"source.":[87],"We":[88],"compare":[89],"these":[90],"solutions":[91],"discuss":[93],"their":[94],"advantages":[95],"disadvantages.":[97],"Our":[98],"is":[101],"work":[104],"with":[105],"ontology":[107],"map":[109],"scraped":[110],"directly":[112],"classes":[114],"attributes.":[116]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
