Natural Language Processing in Humanities

Details

The Women in Machine Learning & Data Science (WiMLDS) Meetup aims to inspire, educate, regardless of gender, and support women and minorities in the field.

All genders may attend our meetups.

---

Agenda

18:00 – Introduction by the Brussels WiMLDS coordinator

18:05 – “Natural Language Processing in Humanities” by M. Fantoli & M. de Lohneux

In this talk, we will discuss how NLP and Humanities research can be combined to, on the one hand, stimulate the research on NLP and, on the other hand, enrich our understanding of historical texts. We will focus on the language of science, particularly the study of The Spirals of Archimedes, one of the most famous mathematicians of the ancient world (and of all times). His work circulated in Early Modern and Modern Europe primarily via a Latin translation by Jacopo da San Cassiano: by describing the process of parsing this text, we show how NLP advanced techniques can support the study of such low-resource and highly specialized languages. First, we introduce the historical and linguistic relevance of Achimedes’ works and their translation. Subsequently, we describe the deep Biaffine parser used for this pilot study. In particular, we motivate the choice of using the technique of treebank embeddings in light of the characteristics of the texts. We will then provide an overview of the training and test data creation process and discuss the results obtained with the parsing. We conclude by reflecting on the advantages and limitations of integrating NLP into Humanities research in light of this experience.

18:50 – Q&A Session

---

Details about the speakers

Margherita Fantoli is Assistant Professor of Digital Humanities at the KU Leuven. With a combined background in Classical Literature (Latin and Ancient Greek) and Mathematics, she works on applying computational methodologies to historical documents. In particular, she is interested in studying Latin scientific texts and the NLP processing of Latin.

Miryam de Lhoneux is Assistant Professor in Natural Language Processing at the department of Computer Science at KU Leuven. She has a background in Linguistics and Artificial Intelligence and works on linguistically informed Natural Language Processing with a focus on multilinguality.