{"id":"https://openalex.org/W2252252584","doi":"https://doi.org/10.3115/v1/w14-0406","title":"The PAIS\u00c0 Corpus of Italian Web Texts","display_name":"The PAIS\u00c0 Corpus of Italian Web Texts","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2252252584","doi":"https://doi.org/10.3115/v1/w14-0406","mag":"2252252584"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-0406","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0406","pdf_url":"https://aclanthology.org/W14-0406.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-0406.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045407805","display_name":"Verena Lyding","orcid":"https://orcid.org/0000-0002-2301-6860"},"institutions":[{"id":"https://openalex.org/I1319360392","display_name":"Eurac Research","ror":"https://ror.org/01xt1w755","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I1319360392"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Verena Lyding","raw_affiliation_strings":["EURAC Research Bolzano/Bozen, IT"],"affiliations":[{"raw_affiliation_string":"EURAC Research Bolzano/Bozen, IT","institution_ids":["https://openalex.org/I1319360392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014048772","display_name":"Egon Stemle","orcid":"https://orcid.org/0000-0002-7655-5526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Egon Stemle","raw_affiliation_strings":["Institute of Computational Linguistics \"Antonio Zam-polli\" -CNR, IT"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics \"Antonio Zam-polli\" -CNR, IT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063159582","display_name":"Claudia Borghetti","orcid":"https://orcid.org/0000-0002-1083-6632"},"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":"Claudia Borghetti","raw_affiliation_strings":["University of Bologna, IT"],"affiliations":[{"raw_affiliation_string":"University of Bologna, IT","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071438615","display_name":"M. Brunello","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marco Brunello","raw_affiliation_strings":["University of Leeds, UK"],"affiliations":[{"raw_affiliation_string":"University of Leeds, UK","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040131603","display_name":"Sara Castagnoli","orcid":"https://orcid.org/0000-0002-9308-7242"},"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":"Sara Castagnoli","raw_affiliation_strings":["University of Bologna, IT"],"affiliations":[{"raw_affiliation_string":"University of Bologna, IT","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084812833","display_name":"Felice Dell\u2019Orletta\u22c4","orcid":"https://orcid.org/0000-0003-3454-9387"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felice Dell'Orletta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029593871","display_name":"Henrik Dittmann","orcid":null},"institutions":[{"id":"https://openalex.org/I2801838318","display_name":"Institut Jules Bordet","ror":"https://ror.org/05e8s8534","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801838318"]},{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["BE","IT"],"is_corresponding":false,"raw_author_name":"Henrik Dittmann","raw_affiliation_strings":["Institut Jules Bordet, BE University of Pisa, IT"],"affiliations":[{"raw_affiliation_string":"Institut Jules Bordet, BE University of Pisa, IT","institution_ids":["https://openalex.org/I2801838318","https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050795259","display_name":"Alessandro Lenci","orcid":"https://orcid.org/0000-0001-5790-4308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Lenci","raw_affiliation_strings":["Institute of Computational Linguistics \"Antonio Zam-polli\" -CNR, IT"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics \"Antonio Zam-polli\" -CNR, IT","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055571560","display_name":"Vito Pirrelli","orcid":"https://orcid.org/0000-0002-5581-7451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vito Pirrelli","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5045407805"],"corresponding_institution_ids":["https://openalex.org/I1319360392"],"apc_list":null,"apc_paid":null,"fwci":11.8399,"has_fulltext":true,"cited_by_count":101,"citation_normalized_percentile":{"value":0.98589088,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.9962999820709229,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9800000190734863,"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":0.5276621580123901},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37202519178390503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33697766065597534},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.32656311988830566},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.32331669330596924},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.32164767384529114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5276621580123901},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37202519178390503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33697766065597534},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.32656311988830566},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.32331669330596924},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.32164767384529114}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.3115/v1/w14-0406","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0406","pdf_url":"https://aclanthology.org/W14-0406.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.6526","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.6526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-0406.pdf","raw_type":"text"},{"id":"pmh:oai:alma.39UBZ_INST:11235273720001241","is_oa":false,"landing_page_url":"http://aclweb.org/anthology/W14-0406","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:arpi.unipi.it:11568/779096","is_oa":true,"landing_page_url":"http://hdl.handle.net/11568/779096","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:cris.unibo.it:11585/399103","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/399103","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/conferenceObject"},{"id":"pmh:oai:it.cnr:prodotti:289308","is_oa":true,"landing_page_url":"http://www.cnr.it/prodotto/i/289308","pdf_url":null,"source":{"id":"https://openalex.org/S7407055101","display_name":"CNR ExploRA","issn_l":null,"issn":null,"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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"info:cnr-pdr/source/autori:Verena Lyding,  Egon Stemle, Claudia Borghetti, Marco Brunello, Sara Castagnoli, Felice Dell'Orletta, Henrik Dittmann, Alessandro Lenci,  Vito Pirrelli/congresso_nome:Corpus annotation, Tree-bank, Corpus design, Corpus harvesting/congresso_luogo:Gothenburg. Sweden/congresso_data:April 26, 2014/anno:2014/pagina_da:36/pagina_a:43/intervallo_pagine:36\u201343","raw_type":"Contributo in atti di convegno"},{"id":"pmh:oai:u-pad.unimc.it:11393/241618","is_oa":false,"landing_page_url":"http://hdl.handle.net/11393/241618","pdf_url":null,"source":{"id":"https://openalex.org/S4377196455","display_name":"U-PAD Unimc - Open Digital Publications (University of Macerata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I55133342","host_organization_name":"University of Macerata","host_organization_lineage":["https://openalex.org/I55133342"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-0406","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0406","pdf_url":"https://aclanthology.org/W14-0406.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8091430692","display_name":null,"funder_award_id":"(MIUR)","funder_id":"https://openalex.org/F4320321873","funder_display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca"}],"funders":[{"id":"https://openalex.org/F4320321873","display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","ror":"https://ror.org/0166hxq48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252252584.pdf","grobid_xml":"https://content.openalex.org/works/W2252252584.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W40340171","https://openalex.org/W84079877","https://openalex.org/W1516428126","https://openalex.org/W1537076907","https://openalex.org/W1600481763","https://openalex.org/W1608699565","https://openalex.org/W1626006465","https://openalex.org/W2014516359","https://openalex.org/W2027979924","https://openalex.org/W2043126905","https://openalex.org/W2105103433","https://openalex.org/W2114663556","https://openalex.org/W2120600278","https://openalex.org/W2138382875","https://openalex.org/W2145003974","https://openalex.org/W2152674344","https://openalex.org/W2250720616","https://openalex.org/W2251936842","https://openalex.org/W2325944896","https://openalex.org/W2782445378","https://openalex.org/W4285719527","https://openalex.org/W4388152432","https://openalex.org/W6677999491"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266"],"abstract_inverted_index":{"Verena":[0],"Lyding,":[1],"Egon":[2],"Stemle,":[3],"Claudia":[4],"Borghetti,":[5],"Marco":[6],"Brunello,":[7],"Sara":[8],"Castagnoli,":[9],"Felice":[10],"Dell\u2019Orletta,":[11],"Henrik":[12],"Dittmann,":[13],"Alessandro":[14],"Lenci,":[15],"Vito":[16],"Pirrelli.":[17],"Proceedings":[18],"of":[19],"the":[20],"9th":[21],"Web":[22],"as":[23],"Corpus":[24],"Workshop":[25],"(WaC-9).":[26],"2014.":[27]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
