Lemmatising Early Modern English: An LLM-assisted experiment
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.
Authors
- Piotr Pęzik (ORCID: https://orcid.org/0000-0003-0019-5840)
- Kamil Andrzejczak (ORCID: https://orcid.org/0000-0001-5838-3575)
- Anna Cichosz (ORCID: https://orcid.org/0000-0002-4095-5632)
- Aleksandra Stasiak (ORCID: https://orcid.org/0000-0002-2620-3856)
- Filip Żarnecki (ORCID: https://orcid.org/0009-0005-1106-408X)
- Jakub Kwiatkowski (ORCID: https://orcid.org/0000-0001-7000-3862)
- Igor Siek
- Aneta Wyczechowska
Institutions
- University of Łódź (PL)
Publication Details
- Journal
- International Journal of Corpus Linguistics
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1075/ijcl.26092.cic
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00