Towards Computational Lexical Semantic Change Detection

Towards Computational Lexical Semantic Change Detection

Today, we lack computational tools for studying lexical and semantic changes at a large scale. Current methods are limited and require huge amounts of text. Studies on semantic change capture only main changes of a single word and offer no possibility to capture the interplay of change in a semantic field.

In this project, we aim to find automatic, corpus-based methods for detecting semantic change and lexical replacement for Swedish and English. We will investigate the fundamental questions of how, when, and why languages change to allow us to quantify language change and shift lexical typological research from small case studies done on limited data sets to larger scales and over wider time spans using various media types and sources.

The results of the project will advance research in NLP and semantics and have practical benefits for researchers in other fields; We aim to facilitate empirical study of language changes themselves, highlight changes for the public to avoid wrongful interpretations and account for language change in large-scale text mining applications such as information extraction and information retrieval. The results will also benefit the public as they access and interpret historical text as well as researchers that wish to track concepts over time without manually finding and accounting for language change.

Project pages

Nina Tahmasebi
Associate Professor in Natural Language Processing