Barbara McGillivray: Data science and historical texts: modelling meaning change from Ancient Greek to web archives
Speaker: Barbara McGillivray (University of Cambridge & The Alan Turing Institute)
Title: Data science and historical texts: modelling meaning change from Ancient Greek to web archives
Over time, new words enter the language, others become obsolete, and existing words acquire new meanings. In Old English thing meant ‘a public assembly’ and now means more generally ‘entity’; chill originally meant ‘to cool’ and has metaphorically been extended to ‘to relax’. The recent digitization efforts have now made it possible to access and mine large digital collections of historical texts using automatic methods and investigate the question of semantic change at an unprecedented scale.
In this seminar I will present my research on developing computational models for semantic change in historical texts, aiming to teach computers to identify such change automatically. I will share my experience of working on Ancient Greek and on large datasets of contemporary English, and will discuss the challenges and opportunities of working in interdisciplinary projects in Data Science, Digital Humanities and Computational Linguistics.
Barbara McGillivray is a research fellow at the University of Cambridge and at The Alan Turing Institute, where she runs the Data Science and Digital Humanities special interest group. She holds a degree in Mathematics and one in Classics from the University of Firenze (Italy), and a PhD in Computational Linguistics from the University of Pisa (2010).