{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:06:18Z","timestamp":1772906778888,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"AEI \/10.13039\/501100011033","award":["PID2023149762NB-100MCIN"],"award-info":[{"award-number":["PID2023149762NB-100MCIN"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>This study presents the first systematic empirical comparison of neural architectures for Universal Dependencies (UD) parsing in Old English, thus addressing central questions in computational historical linguistics and low-resource language processing. We evaluate three approaches\u2014a baseline spaCy pipeline, a pipeline with a pretrained tok2vec component, and a MobileBERT transformer-based model\u2014across datasets ranging from 1000 to 20,000 words. Our results demonstrate that the pretrained tok2vec model consistently outperforms alternatives, because it achieves 83.24% UAS and 74.23% LAS with the largest dataset, whereas the transformer-based approach substantially underperforms despite higher computational costs. Performance analysis reveals that basic tagging tasks reach 85\u201390% accuracy, while dependency parsing achieves approximately 75% accuracy. We identify critical scaling thresholds, with substantial improvements occurring between 1000 and 5000 words and diminishing returns beyond 10,000 words, which provides insights into scaling laws for historical languages. Technical analysis reveals that the poor performance of the transformer stems from parameter-to-data ratio mismatches (1250:1) and the unique orthographic and morphological characteristics of Old English. These findings defy assumptions about transformer superiority in low-resource scenarios and establish evidence-based guidelines for researchers working with historical languages. The broader significance of this study extends to enabling an automated analysis of three million words of extant Old English texts and providing a framework for optimal architecture selection in data-constrained environments. Our results suggest that medium-complexity architectures with monolingual pretraining offer superior cost\u2013benefit trade-offs compared to complex transformer models for historical language processing.<\/jats:p>","DOI":"10.3390\/bdcc9080199","type":"journal-article","created":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:09:27Z","timestamp":1753891767000},"page":"199","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Parsing Old English with Universal Dependencies\u2014The Impacts of Model Architectures and Dataset Sizes"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9900-0104","authenticated-orcid":false,"given":"Javier","family":"Mart\u00edn Arista","sequence":"first","affiliation":[{"name":"Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5356-7391","authenticated-orcid":false,"given":"Ana Elvira","family":"Ojanguren L\u00f3pez","sequence":"additional","affiliation":[{"name":"Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain"}]},{"given":"Sara","family":"Dom\u00ednguez Barrag\u00e1n","sequence":"additional","affiliation":[{"name":"Department of Modern Languages, Universidad de La Rioja, 26006 Logro\u00f1o, LO, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,30]]},"reference":[{"key":"ref_1","unstructured":"Nivre, J., de Marneffe, M.C., Ginter, F., Goldberg, Y., Haji\u010d, J., Manning, C.D., McDonald, R., Petrov, S., Pyysalo, S., and Silveira, N. (2016, January 23\u201328). Universal Dependencies v1: A multilingual treebank collection. Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), Portoro\u017e, Slovenia."},{"key":"ref_2","unstructured":"Nivre, J., de Marneffe, M.C., Ginter, F., Haji\u010d, J., Manning, C.D., Pyysalo, S., Schuster, S., Tyers, F., and Zeman, D. (2020, January 19). Universal Dependencies v2: An evergrowing multilingual treebank collection. Proceedings of the 12th Language Resources and Evaluation Conference, Marseille, France."},{"key":"ref_3","unstructured":"Elena, C., Llu\u00eds, M., Pierre, Z., Aur\u00e9lie, N., and Henning, W. (2024). Universal Dependencies: Principles and practice. Computational Linguistics: Fundamentals and Advances in Natural Language Processing, Springer."},{"key":"ref_4","unstructured":"De Marneffe, M.C., Dozat, T., Silveira, N., Haverinen, K., Ginter, F., Nivre, J., and Manning, C. (2014, January 26\u201331). Universal Stanford Dependencies: A cross-linguistic typology. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), Reykjavik, Iceland."},{"key":"ref_5","first-page":"255","article-title":"Universal Dependencies","volume":"47","author":"Manning","year":"2021","journal-title":"Comput. Linguist."},{"key":"ref_6","unstructured":"De Marneffe, M.C., and Manning, C. (2016). Stanford Typed Dependencies Manual, Stanford University. Technical Report."},{"key":"ref_7","unstructured":"Richard, M.H. (1992). Semantics and Vocabulary. The Cambridge History of the English Language I, Cambridge University Press."},{"key":"ref_8","unstructured":"Campbell, A. (1987). Old English Grammar, Oxford University Press."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Middeke, K. (2022). The Old English Case System: Case and Argument Structure Constructions, Brill.","DOI":"10.1163\/9789004435278"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Fischer, O., van Kemenade, A., Koopman, W., and van der Wurff, W. (2000). The Syntax of Early English, Cambridge University Press.","DOI":"10.1017\/CBO9780511612312"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ringe, D., and Taylor, A. (2014). The Development of Old English, Oxford University Press.","DOI":"10.1093\/acprof:oso\/9780199207848.001.0001"},{"key":"ref_12","unstructured":"Pintzuk, S. (1991). Phrase Structures in Competition: Variation and Change in Old English Word Order. [Ph.D. Thesis, University of Pennsylvania]."},{"key":"ref_13","unstructured":"Pintzuk, S. (1999). Phrase Structures in Competition: Variation and Change in Old English Word Order, Routledge."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Pintzuk, S., Tsoulas, G., and Warner, A. (2000). Verb-object order in Early Middle English. Diachronic Syntax: Models and Mechanisms, Oxford University Press.","DOI":"10.1093\/oso\/9780198250265.001.0001"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1017\/S136067430500153X","article-title":"Transitional syntax: Postverbal pronouns and particles in Old English","volume":"9","author":"Koopman","year":"2005","journal-title":"Engl. Lang. Linguist."},{"key":"ref_16","first-page":"77","article-title":"Revisiting verb (projection) raising in Old English","volume":"6","author":"Haeberli","year":"2006","journal-title":"York Pap. Linguist. Ser. 2"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hogg, R., and Denison, D. (2006). The syntax of Old English. A History of the English Language, Cambridge University Press.","DOI":"10.1017\/CBO9780511791154"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Allen, C. (2008). Genitives in Early English: Typology and Evidence, Oxford University Press.","DOI":"10.1093\/acprof:oso\/9780199216680.001.0001"},{"key":"ref_19","unstructured":"Healey, A., diPaolo Wilkin, J.P., and Xiang, X. (2004). The Dictionary of Old English Web Corpus, Dictionary of Old English Project, Centre for Medieval Studies, University of Toronto."},{"key":"ref_20","unstructured":"Taylor, A., Warner, A., Pintzuk, S., and Beths, F. (2003). The York-Toronto-Helsinki Parsed Corpus of Old English Prose, Department of Language and Linguistic Science, University of York."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Mart\u00edn Arista, J. (2022, January 3\u20135). Old English Universal Dependencies: Categories, Functions and Specific Fields. Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART 2022), Online Streaming, Vienna, Austria.","DOI":"10.5220\/0010977300003116"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"85","DOI":"10.4995\/rlyla.2022.16787","article-title":"Toward the morpho-syntactic annotation of an Old English corpus with Universal Dependencies","volume":"17","year":"2022","journal-title":"Rev. Ling\u00fc\u00edstica Leng. Apl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Mart\u00edn Arista, J. (2024). Toward a Universal Dependencies Treebank of Old English: Representing the Morphological Relatedness of Un-Derivatives. Languages, 9.","DOI":"10.3390\/languages9030076"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mart\u00edn Arista, J., and Ojanguren L\u00f3pez, A.E. (2024). Structuring the Lexicon of Old English with Syntactic Principles: The Role of Deverbal Nominalisations with Aspectual and Control Verbs. Structuring Lexical Data and Digitising Dictionaries. Grammatical Theory, Language Processing and Databases in Historical Linguistics, Brill.","DOI":"10.1163\/9789004702660"},{"key":"ref_25","first-page":"17","article-title":"Old meets new: Universal Dependencies for historical languages","volume":"36","author":"Villa","year":"2023","journal-title":"J. Lang. Technol. Comput. Linguist."},{"key":"ref_26","unstructured":"Mart\u00edn Arista, J. (2023). ParCorOEv3. An Open Access Annotated Parallel Corpus Old English-English, Nerthus Project, Universidad de La Rioja."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1017\/S1351324906004505","article-title":"MaltParser: A language-independent system for data-driven dependency parsing","volume":"13","author":"Nivre","year":"2007","journal-title":"Nat. Lang. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"K\u00fcbler, S., McDonald, R., and Nivre, J. (2009). Dependency Parsing. Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers.","DOI":"10.1007\/978-3-031-02131-2"},{"key":"ref_29","unstructured":"Alexander, F.G. (2011). Part-of-speech tagging from 97% to 100%: Is it time for some linguistics?. Computational Linguistics and Intelligent Text Processing, Springer."},{"key":"ref_30","unstructured":"Wang, Y., Che, W., Tian, J., and Liu, T. (2021, January 1\u20136). Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online, Bangkok, Thailand."},{"key":"ref_31","unstructured":"\u015eahin, G.G. (2020, January 8\u201313). Framing Neural Morphological Tagging for Low-Resource Languages. Proceedings of the 28th International Conference on Computational Linguistics, Online, Barcelona, Spain."},{"key":"ref_32","first-page":"205","article-title":"Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks","volume":"26","author":"Kanerva","year":"2020","journal-title":"Nat. Lang. Eng."},{"key":"ref_33","unstructured":"Augustyniak, \u0141., Morzy, M., Kajdanowicz, T., Kazienko, P., D\u0105browski, M., and \u017belasko, P. (2020, January 29). Punctuation prediction model for conversational speech. Proceedings of the Interspeech 2020, Virtual Event, Shanghai, China."},{"key":"ref_34","unstructured":"Ahmad, W.U., Peng, H., and Chang, K.-W. (2023, January 9\u201314). COLT5: Faster long-range transformers with conditional computation. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada."},{"key":"ref_35","unstructured":"Jurafsky, D., and Martin, J.H. (2020). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition, Prentice-Hall. [2nd ed.]."},{"key":"ref_36","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. (2020). Scaling laws for neural language models. arXiv."},{"key":"ref_37","unstructured":"Rae, J.W., Borgeaud, S., Cai, T., Millican, K., Hoffmann, J., Song, F., Aslanides, J., Henderson, S., Ring, R., and Young, S. (2021). Scaling language models: Methods, analysis & insights from training Gopher. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wong, M.F., and Tan, C.W. (2024). Aligning crowd-sourced human feedback for reinforcement learning on code generation by large language models. IEEE Trans. Big Data, 1\u201312.","DOI":"10.1109\/TBDATA.2024.3524104"},{"key":"ref_39","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 6\u201311). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/8\/199\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:19:25Z","timestamp":1760033965000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/8\/199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,30]]},"references-count":39,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["bdcc9080199"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9080199","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,30]]}}}