This repository contains the scripts, data, and results of a student project in the Master's program in Computational Linguistics at the University of Trier. In this project, we evaluated the extent to which English tenses are represented by BERTs contextual embeddings. The fundamental details of the project are noted in the following poster.
joh-ga/Through-time-with-BERT
Scripts, data, and results from the "Through time with BERT" project, which evaluated and examined the extent to which English tenses are represented in BERT's raw sentence embeddings.
Jupyter Notebook