HumAI: Modeling of meaning and its applications to humanities research
Welcome to the guest lecture in HumAI’s seminar series: Modeling of meaning and its applications to humanities research. This time, we welcome Nina Tahmasebi, Professor at the Department of Philosophy, Linguistics and Theory of Science, and the PI of the research program “Change is Key!”.
About the seminar
In this talk, Nina Tahmasebi will introduce computational modeling of meaning through text and its application to semantic change, that is, how words change meaning over time. She will present some of the recent developments within the research programme Change is Key!, including the use of large language models (LLMs) for definition generation, Janus for the creation of historical sense-annotated data, and the modeling and manual annotation of different types of semantic change.
She will discuss applications of this technology within the humanities and social sciences, showcasing several projects within Change is Key! that use computational modeling to study phenomena such as pluralia tantum and laws of synonymy.
If time permits, she will also present ongoing work aimed at modeling meaning as it is represented in the human mind.
Nina Tahmasebi conducts research on methods for investigating how the meanings of words have changed over time in large collections of text. Her research spans everything from the development of manually annotated texts to computational and evaluation methods, contributing to our understanding of how linguistic methods can be used to study language and language change, as well as changes in societies, cultures, and social norms.
In addition, her research addresses epistemological aspects of robust knowledge production in text-based research using large language models and other forms of artificial intelligence.
AI for the humanities |