{"id":"https://openalex.org/W4308521115","doi":"https://doi.org/10.21437/iberspeech.2022-26","title":"esCorpius: A Massive Spanish Crawling Corpus","display_name":"esCorpius: A Massive Spanish Crawling Corpus","publication_year":2022,"publication_date":"2022-11-08","ids":{"openalex":"https://openalex.org/W4308521115","doi":"https://doi.org/10.21437/iberspeech.2022-26"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2022-26","is_oa":true,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-26","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.21437/iberspeech.2022-26","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087592906","display_name":"Asier Guti\u00e9rrez-Fandi\u00f1o","orcid":"https://orcid.org/0000-0002-7368-6950"},"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"]},{"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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Asier Guti\u00e9rrez-Fandi\u00f1o","raw_affiliation_strings":["LHF Labs Universidad de Granada","LHF Labs University of Edinburgh","Universidad Aut\u00f3noma de Madrid"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LHF Labs Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"LHF Labs University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid","institution_ids":["https://openalex.org/I63634437"]}]},{"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/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]},{"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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"David P\u00e9rez-Fern\u00e1ndez","raw_affiliation_strings":["LHF Labs Universidad de Granada","LHF Labs University of Edinburgh","Universidad Aut\u00f3noma de Madrid"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LHF Labs Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"LHF Labs University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020795476","display_name":"Jordi Armengol-Estap\u00e9","orcid":"https://orcid.org/0000-0001-8893-6185"},"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"]},{"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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Jordi Armengol-Estap\u00e9","raw_affiliation_strings":["LHF Labs Universidad de Granada","LHF Labs University of Edinburgh","Universidad Aut\u00f3noma de Madrid"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LHF Labs Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"LHF Labs University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","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"]},{"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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"David Griol","raw_affiliation_strings":["LHF Labs Universidad de Granada","LHF Labs University of Edinburgh","Universidad Aut\u00f3noma de Madrid"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LHF Labs Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"LHF Labs University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"last","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"]},{"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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Zoraida Callejas","raw_affiliation_strings":["LHF Labs Universidad de Granada","LHF Labs University of Edinburgh","Universidad Aut\u00f3noma de Madrid"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LHF Labs Universidad de Granada","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"LHF Labs University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Universidad Aut\u00f3noma de Madrid","institution_ids":["https://openalex.org/I63634437"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5061,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64456725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9778000116348267,"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":0.9778000116348267,"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/crawling","display_name":"Crawling","score":0.8710048198699951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7146523594856262},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5441293716430664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49516525864601135},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36716902256011963},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3405121862888336},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.048562198877334595}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8710048198699951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146523594856262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5441293716430664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49516525864601135},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36716902256011963},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3405121862888336},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.048562198877334595},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/iberspeech.2022-26","is_oa":true,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-26","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/iberspeech.2022-26","is_oa":true,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-26","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2493916176","https://openalex.org/W2989539713","https://openalex.org/W2993873509","https://openalex.org/W3019166713","https://openalex.org/W3035016936","https://openalex.org/W3105425516","https://openalex.org/W3118781290","https://openalex.org/W3137010024","https://openalex.org/W3169483174","https://openalex.org/W3177765786","https://openalex.org/W3181414820","https://openalex.org/W4226107112","https://openalex.org/W4281609260","https://openalex.org/W4288089799","https://openalex.org/W4292779060"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W2159872134","https://openalex.org/W4299833833","https://openalex.org/W2795447506","https://openalex.org/W2152505903","https://openalex.org/W2963942219","https://openalex.org/W3192589309"],"abstract_inverted_index":{"In":[0],"the":[1,51,99,111,140,151,157],"recent":[2],"years,":[3],"transformer-based":[4],"models":[5],"have":[6,42],"lead":[7],"to":[8,25,164],"significant":[9],"advances":[10],"in":[11,35,53,64,103,110,162],"language":[12,16],"modelling":[13],"for":[14],"natural":[15],"processing.However,":[17],"they":[18,59],"require":[19],"a":[20,31,71,85,124,132],"vast":[21],"amount":[22],"of":[23,33,94,108,116,134,142],"data":[24,120],"be":[26],"(pre-)trained":[27],"and":[28,78,114,130,145,156],"there":[29],"is":[30,98],"lack":[32],"corpora":[34],"languages":[36],"other":[37,67],"than":[38],"English.Recently,":[39],"several":[40],"initiatives":[41],"presented":[43],"multilingual":[44],"datasets":[45],"obtained":[46,89],"from":[47,75,90],"automatic":[48],"web":[49,117,153],"crawling.However,":[50],"results":[52],"Spanish":[54,86,104],"present":[55,70],"important":[56],"shortcomings,":[57],"as":[58],"are":[60],"either":[61],"too":[62],"small":[63],"comparison":[65],"with":[66,105,166],"languages,":[68],"or":[69],"low":[72],"quality":[73,109],"derived":[74],"sub-optimal":[76],"cleaning":[77,128],"deduplication.In":[79],"this":[80,106],"paper,":[81],"we":[82,148],"introduce":[83],"ESCORPIUS,":[84],"crawling":[87],"corpus":[88,102],"near":[91],"1":[92],"Pb":[93],"Common":[95],"Crawl":[96],"data.It":[97],"most":[100],"extensive":[101],"level":[107],"extraction,":[112],"purification":[113],"deduplication":[115,135],"textual":[118],"content.Our":[119],"curation":[121],"process":[122],"involves":[123],"novel":[125],"highly":[126],"parallel":[127],"pipeline":[129],"encompasses":[131],"series":[133],"mechanisms":[136],"that":[137],"together":[138],"ensure":[139],"integrity":[141],"both":[143,150],"document":[144],"paragraph":[146],"boundaries.Additionally,":[147],"maintain":[149],"source":[152],"page":[154],"URL":[155,161],"WARC":[158],"shard":[159],"origin":[160],"order":[163],"complain":[165],"EU":[167],"regulations.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
