{"id":"https://openalex.org/W4393496585","doi":"https://doi.org/10.5281/zenodo.8220853","title":"ChatSubs: A dataset of movie dialogues in Spanish, Catalan, Basque and Galician","display_name":"ChatSubs: A dataset of movie dialogues in Spanish, Catalan, Basque and Galician","publication_year":2023,"publication_date":"2023-07-27","ids":{"openalex":"https://openalex.org/W4393496585","doi":"https://doi.org/10.5281/zenodo.8220853"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:8220853","is_oa":true,"landing_page_url":"https://zenodo.org/record/8220853","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/8220853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026771410","display_name":"Ksenia Kharitonova","orcid":"https://orcid.org/0000-0002-9139-2622"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ksenia Kharitonova","raw_affiliation_strings":["Department of Software Engineering, University of Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9139-2622","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057526407","display_name":"Zoraida Callejas","orcid":"https://orcid.org/0000-0001-8891-5237"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Zoraida Callejas","raw_affiliation_strings":["Department of Software Engineering and Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8891-5237","affiliations":[{"raw_affiliation_string":"Department of Software Engineering and Research Centre for Information and Communication Technologies (CITIC-UGR), University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069797573","display_name":"David P\u00e9rez\u2010Fern\u00e1ndez","orcid":"https://orcid.org/0000-0002-2214-0245"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David P\u00e9rez-Fern\u00e1ndez","raw_affiliation_strings":["Universidad Aut\u00f3noma de Madrid, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-2214-0245","affiliations":[{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087592906","display_name":"Asier Guti\u00e9rrez-Fandi\u00f1o","orcid":"https://orcid.org/0000-0002-7368-6950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asier Guti\u00e9rrez-Fandi\u00f1o","raw_affiliation_strings":["LHF Labs, Bilbao, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7368-6950","affiliations":[{"raw_affiliation_string":"LHF Labs, Bilbao, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019802248","display_name":"David Griol","orcid":"https://orcid.org/0000-0001-6266-5321"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Griol","raw_affiliation_strings":["Department of Software Engineering, University of Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6266-5321","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, University of Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9144999980926514,"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"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9144999980926514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/catalan","display_name":"Catalan","score":0.9766334891319275},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.4131261110305786},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35570406913757324},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.32755106687545776},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.28114980459213257},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.2512626647949219},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07862550020217896}],"concepts":[{"id":"https://openalex.org/C164105321","wikidata":"https://www.wikidata.org/wiki/Q7026","display_name":"Catalan","level":2,"score":0.9766334891319275},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.4131261110305786},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35570406913757324},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.32755106687545776},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.28114980459213257},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.2512626647949219},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07862550020217896}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:8220853","is_oa":true,"landing_page_url":"https://zenodo.org/record/8220853","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.8220853","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8220853","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:8220853","is_oa":true,"landing_page_url":"https://zenodo.org/record/8220853","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2077845850","https://openalex.org/W2486167700","https://openalex.org/W613669934","https://openalex.org/W2904571626","https://openalex.org/W2945415727","https://openalex.org/W2946010871","https://openalex.org/W1494937920","https://openalex.org/W2308616044","https://openalex.org/W1482410789"],"abstract_inverted_index":{"Description:":[0],"The":[1,32],"ChatSubs":[2],"dataset":[3,33],"contains":[4],"dialogues":[5,29,43],"in":[6,67,71],"Spanish":[7],"and":[8,16,23,30,44,75],"three":[9],"co-official":[10],"languages":[11],"of":[12,35,51],"Spain":[13],"(Catalan,":[14],"Basque,":[15,74],"Galician).":[17],"It":[18,57],"was":[19],"obtained":[20],"from":[21],"OpenSubtitles":[22],"processed":[24],"to":[25],"generate":[26],"clearly":[27],"segmented":[28],"turns.":[31],"consists":[34],"206,706":[36],"JSON":[37],"files,":[38],"with":[39],"over":[40],"20":[41],"million":[42,46],"96":[45],"turns,":[47],"making":[48],"it":[49],"one":[50],"the":[52],"largest":[53],"dialogue":[54,69],"corpora":[55],"available.":[56],"serves":[58],"as":[59],"an":[60],"excellent":[61],"resource":[62],"for":[63],"research":[64],"teams":[65],"interested":[66],"training":[68],"models":[70],"Spanish,":[72],"Catalan,":[73],"Galician.":[76],"License:":[77],"CC":[78],"BY-NC":[79],"4.0.":[80]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
