Article In: International Journal of Corpus Linguistics: Online-First Articles
Lemmatising Early Modern English
An LLM-assisted experiment
This content is being prepared for publication; it may be subject to changes.
Abstract
In the reported experiment, our team developed an LLM-assisted procedure for the lemmatisation of the Penn-Helsinki Parsed
Corpus of Early Modern English (PPCEME), and Early Modern English (EME) in general. First, we engineered a set of annotation guidelines for
lemmatising word forms found in PPCEME on the basis of context and morphosyntactic tags. The lemmatisations were checked manually by a team
of annotators and the overall accuracy of the procedure based on GPT-4o-mini was between 95% and 97%, with some bypasses applied. The paper
presents an in-depth quantitative and qualitative analysis of the results, where the main advantages and weaknesses of the model are
identified. The LLM-based procedure is also compared to VARD, a popular tool used for normalising EME spelling. Finally, we also fine-tuned
a smaller specialised model aimed at lemmatising EME texts, for which we report the highest accuracy values of 96–97% on held-out evaluation
datasets.
Keywords: Early Modern English, lemmatisation, LLM, historical corpora
Article outline
- 1.Introduction
- 2.EME spelling: Challenges for automatic lemmatisation
- 3.Existing tools and resources
- 4.Methodology
- 4.1Lemmatisation guidelines
- 4.2Prompt engineering and model selection
- 5.Results
- 5.1Content words
- 5.2Proper nouns and numerals
- 5.3Function words
- 5.4Comparison to VARD
- 6.Towards a generalised procedure of lemmatising EME
- 6.1Annotation-free lemmatisation
- 6.2Held-out test sets
- 6.3Fine-tuning open-weight LLMs for EME lemmatisation
- 7.Conclusions
- Notes
- Author queries
References
References (28)
Archer, D. E., Kytö, M., Baron, A., & Rayson, P. (2015). Guidelines
for normalising Early Modern English corpora: Decisions and justifications. ICAME
Journal, 39(1), 5–24.
Baron, A., & Rayson, P. (2008). VARD2:
a tool for dealing with spelling variation in historical corpora. Paper presented
at: Postgraduate conference in corpus linguistics, Aston
University, Birmingham. [URL]
Bollmann, M., Bingel, J., & Søgaard, A. (2017). Learning
attention for historical text normalization by learning to pronounce. In R. Barzilay & M.-Y. Kan (Eds.), Proceedings
of the 55th Annual Meeting of the Association for Computational
Linguistics (pp. 332–344). Association for Computational Linguistics.
Brengelman, F. (1980). Orthoepists,
printers and the rationalisation of English spelling. Journal of English and Germanic
Philology, 79, 332–354.
Cichosz, A., Pęzik, P., Grabski, M., Adamczyk, M., Rybińska, P., & Ostrowska, A. (2021). The
VARIOE online morphological dictionary for YCOE. University of Łódź. [URL]
Davies, M. (2017). Early
English Books Online (EEBO). [URL]
Fix, H. (1980). Automatische
Normalisierung: Vorarbeit zur Lemmatisierung eines diplomatischen altisländischen
Textes. In P. Sappler & E. Straßner (Eds.), Maschinelle
Verarbeitung altdeutscher Texte: Beiträge zum dritten Symposion, Tübingen, 17.–19. Februar
1977 (pp. 92–100). Niemeyer.
Hämäläinen, M., Säily, T., Rueter, J., Tiedemann, J., & Mäkelä, E. (2018). Normalizing
Early English letters to present-day English spelling. In B. Alex, S. Degaetano-Ortlieb, A. Feldman, A. Kazantseva, N. Reiter, & S. Szpakowicz (Eds.), Proceedings
of the second joint SIGHUM workshop on computational linguistics for cultural heritage, social sciences, humanities and
literature (pp. 87–96). Association for Computational Linguistics. [URL]
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021). LoRA:
Low-rank adaptation of large language models. arXiv:2106.09685v2. [URL]
Kalai, A. T., Nachum, O., Vempala, S. S., & Zhang, E. (2025). Why
language models hallucinate. arXiv:2509.04664v1. [URL]
Koller, G. (1983). Ein
maschinelles Verfahren zur Normalisierung altdeutscher Texte. In D. Peschel (Ed.), Germanistik
in
Erlangen (pp. 611–620). Universitätsbund Erlangen-Nürnberg.
Kroch, A., Santorini, B., & Delfs, L. (2004). The
Penn-Helsinki Parsed Corpus of Early Modern English (PPCEME). Department of Linguistics, University of Pennsylvania. [URL]
Ljubešić, N., Zupan, K., Fišer, D., & Erjavec, T. (2016). Normalising
Slovene data: Historical texts vs. user-generated content. In S. Dipper, F. Neubarth, & H. Zinsmeister (Eds.), Proceedings
of the 13th conference on natural language processing (KONVENS
2016) (pp. 146–155). Bochumer Linguistische Arbeitsberichte.
Kurath, H., Kuhn, S. M., & Lewis, R. E. (Eds.). (1952–2001). Middle
English Dictionary (MED). University of Michigan Press. [URL]
Moessner, L. (2012). Early
Modern English: Standardization. In A. Bergs & L. J. Brinton (Eds.), English
historical linguistics: An international
handbook (pp. 698–713). De Gruyter Mouton.
Nevalainen, T., Kaislaniemi, S., Säily, T., Laitinen, M., Nevala, M., Nurmi, A., Palander-Collin, M., Sairio, A., Raumolin-Brunberg, H., & Saario, L. (2021). Corpus
of Early English Correspondence Extension Sampler Part 1 (CEECES
1). VARIENG.
Nevalainen, T., & Raumolin-Brunberg, H. (2003). Historical
sociolinguistics: Language change in Tudor and Stuart
England. Longman.
Oxford English
Dictionary. (n.d.). Oxford University Press. [URL]
Oravecz, C., Sass, B., & Simon, E. (2010). Semi-automatic
normalization of Old Hungarian codices. In C. Sporleder, & K. Zervanou (Eds.), Proceedings
of the ECAI 2010 workshop on language technology for cultural
heritage (pp. 55–59). University of Lisbon.
Pettersson, E., Megyesi, B., & Nivre, J. (2013). Normalisation
of historical text using context-sensitive weighted Levenshtein distance and compound
splitting. In S. Oepen, K. Hagen, & J. Bondi Johannessen (Eds.), Proceedings
of the 19th Nordic conference of computational linguistics (NODALIDA
2013) (pp. 163–179). Linköping University Electronic Press. [URL]
Rayson, P., Archer, D., & Smith, N. (2005). VARD
versus Word: A comparison of the UCREL variant detector and modern spell checkers on English historical
corpora. In P. Danielsson, & M. Wagenmakers (Eds.), Proceedings
of the Corpus Linguistics conference (CL2005). University of Birmingham.
Roh, H., Miller, C., & Syafiq, E. A. (2026). Efficient
large language models for modernizing Early Modern English texts. Conference camera-ready paper, Virginia
Tech. [URL]
Salmon, V. (1999). Orthography
and punctuation. In R. Lass (Ed.), The
Cambridge history of the English language — Volume 3:
1476–1776 (pp. 13–55). Cambridge University Press.
Tieken-Boon van Ostade, I. (1998). Standardization
of English spelling: The eighteenth-century printers’ contribution. In J. Fisiak & M. Krygier (Eds), Advances
in English historical
linguistics (pp. 457–470). De Gruyter Mouton.
Vidal-Gorène, C., Kindt, B., & Cafiero, F. (2026). Under-resourced
studies of under-resourced languages: Lemmatization and POS-tagging with LLM annotators for historical Armenian, Georgian, Greek and
Syriac. In H. Hettiarachchi, T. Ranasinghe, A. Plum, P. Rayson, R. Mitkov, M. Gaber, D. Premasiri, F. Anting Tan, & L. Uyangodage (Eds.), Proceedings
of the Second Workshop on Language Models for Low-Resource Languages (LoResLM
2026) (pp. 324–334). Association for Computational Linguistics.