Whatever it takes to understand a central banker - Embedding their words using neural networks
Martin Baumgaertner () and
Johannes Zahner ()
Additional contact information
Martin Baumgaertner: THM Business School
Johannes Zahner: Philipps-Universitaet Marburg
Authors registered in the RePEc Author Service: Martin Baumgärtner ()
MAGKS Papers on Economics from Philipps-Universität Marburg, Faculty of Business Administration and Economics, Department of Economics (Volkswirtschaftliche Abteilung)
Dictionary approaches are at the forefront of current techniques for quantifying central bank communication. This paper proposes embeddings â€“ a language model trained using machine learning techniques â€“ to locate words and documents in a multidimensional vector space. To accomplish this, we gather a text corpus that is unparalleled in size and diversity in the central bank communication literature, as well as introduce a novel approach to text quantification from computational linguistics. Utilizing this novel text corpus of over 23,000 documents from over 130 central banks we are able to provide high quality text-representations â€“embeddingsâ€“ for central banks. Finally, we demonstrate the applicability of embeddings in this paper by several examples in the fields of monetary policy surprises, financial uncertainty, and gender bias.
Keywords: Word Embedding; Neural Network; Central Bank Communication; Natural Language Processing; Transfer Learning (search for similar items in EconPapers)
JEL-codes: C45 C53 E52 Z13 (search for similar items in EconPapers)
Pages: 45 pages
New Economics Papers: this item is included in nep-big, nep-cba, nep-cmp, nep-isf, nep-mac and nep-mon
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed
Downloads: (external link)
https://www.uni-marburg.de/en/fb02/research-groups ... 2021_baumgartner.pdf First 202130 (application/pdf)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:mar:magkse:202130
Access Statistics for this paper
More papers in MAGKS Papers on Economics from Philipps-Universität Marburg, Faculty of Business Administration and Economics, Department of Economics (Volkswirtschaftliche Abteilung) Contact information at EDIRC.
Bibliographic data for series maintained by Bernd Hayo ().