Translation and NER

Abstract The Prize Papers collection includes a wealth of early modern logbooks in various languages, posing challenges for researchers when trying to obtain place and time information, e.g. to visualize shipping routes. Our approach is to use machine translation in order to enhance access to named entity recognition (NER) models. This comparative analysis of spaCy and GLiNER demonstrates that machine translation can improve NER for 18th century logbooks in Dutch, English and French, though this methodology requires careful consideration of trade-offs between improved accessibility and potential loss of historical nuance. Nonetheless, it offers new possibilities for linking translation history with spatial information and allows for large-scale analyses of early modern maritime networks.