{"id":"https://openalex.org/W2155870214","doi":"https://doi.org/10.1007/s10579-009-9081-4","title":"The WaCky wide web: a collection of very large linguistically processed web-crawled corpora","display_name":"The WaCky wide web: a collection of very large linguistically processed web-crawled corpora","publication_year":2009,"publication_date":"2009-02-09","ids":{"openalex":"https://openalex.org/W2155870214","doi":"https://doi.org/10.1007/s10579-009-9081-4","mag":"2155870214"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-009-9081-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10579-009-9081-4","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-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/A5038612405","display_name":"Marco Baroni","orcid":"https://orcid.org/0000-0001-5066-3580"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Marco Baroni","raw_affiliation_strings":["CIMeC, University of Trento, Rovereto, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIMeC, University of Trento, Rovereto, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063046436","display_name":"Silvia Bernardini","orcid":"https://orcid.org/0000-0003-0750-4861"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvia Bernardini","raw_affiliation_strings":["SITLeC, University of Bologna, Forl\u00ec, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SITLeC, University of Bologna, Forl\u00ec, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067980261","display_name":"Adriano Ferraresi","orcid":"https://orcid.org/0000-0002-6957-0605"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Adriano Ferraresi","raw_affiliation_strings":["SITLeC, University of Bologna, Forl\u00ec, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SITLeC, University of Bologna, Forl\u00ec, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055043903","display_name":"Eros Zanchetta","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Eros Zanchetta","raw_affiliation_strings":["SITLeC, University of Bologna, Forl\u00ec, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SITLeC, University of Bologna, Forl\u00ec, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038612405"],"corresponding_institution_ids":["https://openalex.org/I193223587"],"apc_list":null,"apc_paid":null,"fwci":56.5974,"has_fulltext":false,"cited_by_count":1197,"citation_normalized_percentile":{"value":0.99916142,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"43","issue":"3","first_page":"209","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T12353","display_name":"Lexicography and Language Studies","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.977400004863739,"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":0.7942590713500977},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7236815094947815},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5575717091560364},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5310894250869751},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5156010985374451},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5079436898231506},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4808114767074585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4290027618408203},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.417781263589859},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.40937668085098267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942590713500977},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7236815094947815},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5575717091560364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5310894250869751},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5156010985374451},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5079436898231506},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4808114767074585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4290027618408203},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.417781263589859},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40937668085098267},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10579-009-9081-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10579-009-9081-4","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:cris.unibo.it:11585/83043","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/83043","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.unitn.it:11572/6917","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/6917","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W53767355","https://openalex.org/W88750847","https://openalex.org/W205260337","https://openalex.org/W574949657","https://openalex.org/W1505715096","https://openalex.org/W1543096214","https://openalex.org/W1578617886","https://openalex.org/W1613484676","https://openalex.org/W1983802535","https://openalex.org/W1998038442","https://openalex.org/W2014516359","https://openalex.org/W2039447541","https://openalex.org/W2058233873","https://openalex.org/W2073865254","https://openalex.org/W2104630935","https://openalex.org/W2115054880","https://openalex.org/W2116780029","https://openalex.org/W2152565070","https://openalex.org/W2158915197","https://openalex.org/W2170571488","https://openalex.org/W2285453998","https://openalex.org/W2339784187","https://openalex.org/W3165616014","https://openalex.org/W4211138600","https://openalex.org/W4250603334","https://openalex.org/W6602210249","https://openalex.org/W6608350269","https://openalex.org/W6795365444","https://openalex.org/W6909306877"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W2171573941","https://openalex.org/W4360873893","https://openalex.org/W2144007828","https://openalex.org/W3040878054"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":69},{"year":2023,"cited_by_count":57},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":80},{"year":2020,"cited_by_count":90},{"year":2019,"cited_by_count":84},{"year":2018,"cited_by_count":129},{"year":2017,"cited_by_count":70},{"year":2016,"cited_by_count":119},{"year":2015,"cited_by_count":85},{"year":2014,"cited_by_count":100},{"year":2013,"cited_by_count":86},{"year":2012,"cited_by_count":64}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}
