- About
- Convenor
About
The Bid Development Award helped prepare a bid to implement new computational methods for the analysis of language change in ancient languages over the last two millennia. Philologists have long practised the art of ‘reading texts slowly’, elucidating word meanings though analysis of context and text structures; conversely, algorithms can perform advanced processing of texts at scale. Currently these models of knowledge processing exist in isolation. This project’s goal is to achieve a synergy between historical linguists and algorithms with a new research model holistically integrating the two. The project’s main objective is to develop algorithms that model meaning change in Latin and ancient Greek based on text data combined with expert knowledge and contextual information, and a series of comprehensive analyses shedding new light on the interaction between meaning and its historical contexts over time.
Convenor
- Dr Barbara McGillivray (Senior Research Associate in the Faculty of Modern and Medieval Languages and Linguistics (Theoretical and Applied Linguistics), University of Cambridge)
Dr Barbara McGillivray is a Senior Research Associate in the Faculty of Modern and Medieval Languages and Linguistics (Theoretical and Applied Linguistics), University of Cambridge, and Turing Research Fellow at The Alan Turing Institute. She is editor-in-chief of the Journal of Open Humanities Data, founder and convenor of the Humanities and Data Science Turing special interest group and Co-Investigator of the Living with Machines project. She has a degree in Classics and a degree in Mathematics, and her PhD was on computational linguistics for Latin. She has worked as a language technologist in the Dictionaries division of Oxford University Press and as a data scientist in the Open Research Group of Springer Nature.
Barbara’s research lies at the intersection between computational linguistics and historical linguistics. Her current research focusses on computational models of word meaning change in historical texts using machine learning methods combined with digital humanities expertise.
