{"id":"https://openalex.org/W4412749190","doi":"https://doi.org/10.3390/bdcc9080199","title":"Parsing Old English with Universal Dependencies\u2014The Impacts of Model Architectures and Dataset Sizes","display_name":"Parsing Old English with Universal Dependencies\u2014The Impacts of Model Architectures and Dataset Sizes","publication_year":2025,"publication_date":"2025-07-30","ids":{"openalex":"https://openalex.org/W4412749190","doi":"https://doi.org/10.3390/bdcc9080199"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9080199","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9080199","pdf_url":null,"source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/bdcc9080199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070769890","display_name":"Francisco Javier Mart\u00edn Arista","orcid":"https://orcid.org/0000-0001-9900-0104"},"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"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Mart\u00edn Arista","raw_affiliation_strings":["Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain","institution_ids":["https://openalex.org/I168974976"]}]},{"author_position":"middle","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"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ana Elvira Ojanguren L\u00f3pez","raw_affiliation_strings":["Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain","institution_ids":["https://openalex.org/I168974976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050941713","display_name":"Sara Dom\u00ednguez Barrag\u00e1n","orcid":"https://orcid.org/0000-0002-1552-0581"},"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"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sara Dom\u00ednguez Barrag\u00e1n","raw_affiliation_strings":["Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain","institution_ids":["https://openalex.org/I168974976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070769890"],"corresponding_institution_ids":["https://openalex.org/I168974976"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.7978,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9158372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"9","issue":"8","first_page":"199","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9850999712944031,"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/parsing","display_name":"Parsing","score":0.7414548397064209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6986515522003174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49127811193466187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48443058133125305}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7414548397064209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6986515522003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49127811193466187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48443058133125305}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/bdcc9080199","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9080199","pdf_url":null,"source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8eef61e9f104463a9bc038204c257b5b","is_oa":true,"landing_page_url":"https://doaj.org/article/8eef61e9f104463a9bc038204c257b5b","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 9, Iss 8, p 199 (2025)","raw_type":"article"},{"id":"pmh:oai:portal.dialnet.es:doc/68c5b70a8237274acbcc1ce7","is_oa":true,"landing_page_url":"https://investigacion.unirioja.es/documentos/68c5b70a8237274acbcc1ce7","pdf_url":null,"source":{"id":"https://openalex.org/S4306402551","display_name":"RIUR (Universidad de La Rioja)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3032752892","host_organization_name":"Universidad Internacional de La Rioja","host_organization_lineage":["https://openalex.org/I3032752892"],"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":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.3390/bdcc9080199","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9080199","pdf_url":null,"source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W429665430","https://openalex.org/W1515847863","https://openalex.org/W1543602800","https://openalex.org/W1555848040","https://openalex.org/W1568793342","https://openalex.org/W1874618452","https://openalex.org/W1962622193","https://openalex.org/W2032026403","https://openalex.org/W2130776479","https://openalex.org/W2495851293","https://openalex.org/W2579343286","https://openalex.org/W2604763608","https://openalex.org/W2915977242","https://openalex.org/W2985021021","https://openalex.org/W3018647120","https://openalex.org/W3029683630","https://openalex.org/W3176096162","https://openalex.org/W4212964987","https://openalex.org/W4288080405","https://openalex.org/W4301881503","https://openalex.org/W4327990750","https://openalex.org/W4388122918","https://openalex.org/W4392197637","https://openalex.org/W4393984022","https://openalex.org/W4405908042","https://openalex.org/W6639150004","https://openalex.org/W6758712795"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830","https://openalex.org/W1502858101","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"study":[1,187],"presents":[2],"the":[3,61,77,81,140,144,153],"first":[4],"systematic":[5],"empirical":[6],"comparison":[7],"of":[8,143,159,185,194,198],"neural":[9],"architectures":[10,219],"for":[11,133,176,207,232],"Universal":[12],"Dependencies":[13],"(UD)":[14],"parsing":[15,102],"in":[16,23,169,211],"Old":[17,160,200],"English,":[18],"thus":[19],"addressing":[20],"central":[21],"questions":[22],"computational":[24,88],"historical":[25,134,180,233],"linguistics":[26],"and":[27,45,73,118,121,152,156,172,203],"low-resource":[28,170],"language":[29,234],"processing.":[30,235],"We":[31,107],"evaluate":[32],"three":[33,195],"approaches\u2014a":[34],"baseline":[35],"spaCy":[36],"pipeline,":[37],"a":[38,41,46,205],"pipeline":[39],"with":[40,76,112,179,220],"pretrained":[42,62],"tok2vec":[43,63],"component,":[44],"MobileBERT":[47],"transformer-based":[48,82],"model\u2014across":[49],"datasets":[50],"ranging":[51],"from":[52,147],"1000":[53,117],"to":[54,189,228],"20,000":[55],"words.":[56],"Our":[57,214],"results":[58,215],"demonstrate":[59],"that":[60,93,139,217],"model":[64],"consistently":[65],"outperforms":[66],"alternatives,":[67],"because":[68],"it":[69],"achieves":[70,103],"83.24%":[71],"UAS":[72],"74.23%":[74],"LAS":[75],"largest":[78],"dataset,":[79],"whereas":[80],"approach":[83],"substantially":[84],"underperforms":[85],"despite":[86],"higher":[87],"costs.":[89],"Performance":[90],"analysis":[91,137,193],"reveals":[92,138],"basic":[94],"tagging":[95],"tasks":[96],"reach":[97],"85\u201390%":[98],"accuracy,":[99],"while":[100],"dependency":[101],"approximately":[104],"75%":[105],"accuracy.":[106],"identify":[108],"critical":[109],"scaling":[110,131],"thresholds,":[111],"substantial":[113],"improvements":[114],"occurring":[115],"between":[116],"5000":[119],"words":[120,197],"diminishing":[122],"returns":[123],"beyond":[124],"10,000":[125],"words,":[126],"which":[127],"provides":[128],"insights":[129],"into":[130],"laws":[132],"languages.":[135,181],"Technical":[136],"poor":[141],"performance":[142],"transformer":[145,167,230],"stems":[146],"parameter-to-data":[148],"ratio":[149],"mismatches":[150],"(1250:1)":[151],"unique":[154],"orthographic":[155],"morphological":[157],"characteristics":[158],"English.":[161],"These":[162],"findings":[163],"defy":[164],"assumptions":[165],"about":[166],"superiority":[168],"scenarios":[171],"establish":[173],"evidence-based":[174],"guidelines":[175],"researchers":[177],"working":[178],"The":[182],"broader":[183],"significance":[184],"this":[186],"extends":[188],"enabling":[190],"an":[191],"automated":[192],"million":[196],"extant":[199],"English":[201],"texts":[202],"providing":[204],"framework":[206],"optimal":[208],"architecture":[209],"selection":[210],"data-constrained":[212],"environments.":[213],"suggest":[216],"medium-complexity":[218],"monolingual":[221],"pretraining":[222],"offer":[223],"superior":[224],"cost\u2013benefit":[225],"trade-offs":[226],"compared":[227],"complex":[229],"models":[231]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}