{"id":"https://openalex.org/W7134196037","doi":"https://doi.org/10.1109/bigdata66926.2025.11401721","title":"Scaling Classical NLP Pipelines for Underresourced Old English: Character-Level Models, Unsupervised Pretraining, and Supervised Data Growth","display_name":"Scaling Classical NLP Pipelines for Underresourced Old English: Character-Level Models, Unsupervised Pretraining, and Supervised Data Growth","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7134196037","doi":"https://doi.org/10.1109/bigdata66926.2025.11401721"},"language":null,"primary_location":{"id":"doi:10.1109/bigdata66926.2025.11401721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","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/A5110846325","display_name":"Javier Martin Arista","orcid":null},"institutions":[{"id":"https://openalex.org/I168974976","display_name":"Universidad de La Rioja","ror":"https://ror.org/0553yr311","country_code":"ES","type":"education","lineage":["https://openalex.org/I168974976"]},{"id":"https://openalex.org/I4210162122","display_name":"Gobierno de La Rioja","ror":"https://ror.org/05cjrnv40","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210162122"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Mart\u00edn Arista","raw_affiliation_strings":["University of La Rioja,Department of Modern Languages,Logro&#x00F1;o,Spain"],"affiliations":[{"raw_affiliation_string":"University of La Rioja,Department of Modern Languages,Logro&#x00F1;o,Spain","institution_ids":["https://openalex.org/I168974976","https://openalex.org/I4210162122"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039355848","display_name":"Dar\u00edo Metola Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-7980-7098"},"institutions":[{"id":"https://openalex.org/I168974976","display_name":"Universidad de La Rioja","ror":"https://ror.org/0553yr311","country_code":"ES","type":"education","lineage":["https://openalex.org/I168974976"]},{"id":"https://openalex.org/I4210162122","display_name":"Gobierno de La Rioja","ror":"https://ror.org/05cjrnv40","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210162122"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dar\u00edo Metola Rodr\u00edguez","raw_affiliation_strings":["University of La Rioja,Department of Modern Languages,Logro&#x00F1;o,Spain"],"affiliations":[{"raw_affiliation_string":"University of La Rioja,Department of Modern Languages,Logro&#x00F1;o,Spain","institution_ids":["https://openalex.org/I168974976","https://openalex.org/I4210162122"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023332452","display_name":"Ana Elvira Ojanguren L\u00f3pez","orcid":"https://orcid.org/0000-0001-5356-7391"},"institutions":[{"id":"https://openalex.org/I168974976","display_name":"Universidad de La Rioja","ror":"https://ror.org/0553yr311","country_code":"ES","type":"education","lineage":["https://openalex.org/I168974976"]},{"id":"https://openalex.org/I4210162122","display_name":"Gobierno de La Rioja","ror":"https://ror.org/05cjrnv40","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210162122"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ana Elvira Ojanguren L\u00f3pez","raw_affiliation_strings":["University of La Rioja,Department of Modern Languages,Logro&#x00F1;o,Spain"],"affiliations":[{"raw_affiliation_string":"University of La Rioja,Department of Modern Languages,Logro&#x00F1;o,Spain","institution_ids":["https://openalex.org/I168974976","https://openalex.org/I4210162122"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110846325"],"corresponding_institution_ids":["https://openalex.org/I168974976","https://openalex.org/I4210162122"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88675862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5482","last_page":"5489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7355999946594238,"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":0.7355999946594238,"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/T12090","display_name":"Language and cultural evolution","score":0.06780000030994415,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.049400001764297485,"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/scaling","display_name":"Scaling","score":0.4138999879360199},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.39559999108314514},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.391400009393692},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3479999899864197},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.31150001287460327},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.31029999256134033}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6908000111579895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.559499979019165},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3862000107765198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata66926.2025.11401721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4035354554653168}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W35086054","https://openalex.org/W2251386579","https://openalex.org/W2493916176","https://openalex.org/W2735393842","https://openalex.org/W2896457183","https://openalex.org/W2915977242","https://openalex.org/W2950176361","https://openalex.org/W2970529259","https://openalex.org/W3034457371","https://openalex.org/W3035390927","https://openalex.org/W3037109418","https://openalex.org/W4386566383","https://openalex.org/W7131798324"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-09T07:06:17.341095","created_date":"2026-03-09T00:00:00"}
