Answers are grounded in this paper and cite their sources.
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.
No takes yet. Share an insight, caveat, or question.
Cichosz et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: