Abstract This paper investigates the ability of Generative Pre-training Transformer (GPT)
models to decipher Fedspeak, a term used to describe the technical language used by the …

Dictionary approaches are at the forefront of current techniques for quantifying central bank
communication. This paper proposes embeddings-a language model trained using machine …

For simple classification tasks, we show that users can benefit from the advantages of using
small, local, generative language models instead of large commercial models without a …

Based on a record of dissents on FOMC votes and transcripts of the meetings from 1976 to
2017, we develop a deep learning model based on self-attention modules to create a …

This study analyzes the readability and sentiment of central bank communications across six
Central and Eastern European countries. It reveals considerable variability in readability …

Although central bank communication is a core monetary policy and accountability tool for
central banks, little is known about what shapes it. This paper develops and tests a theory …

This paper introduces a novel database of text features extracted from the speeches of 53
central banks from 1996 to 2023 using state-of-the-art NLP methods. We establish four …

Over the last few decades, there has been an increase in the analysis and interpretation of
central bank communication (Blinder et al., 2008). This development was accelerated by the …

This thesis evaluates the effectiveness of different Natural Language Processing (NLP)
sentiment models in predicting the inflation expectations of economic agents based on the …

This paper studies time-series patterns in the contribution of macroeconomic shocks to the
variation in US Treasury bond yields. I consider a term structure model with time-varying …