Arbeitspapier

Whatever it takes to understand a central banker: Embedding their words using neural networks

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

Sprache
Englisch

Erschienen in
Series: MAGKS Joint Discussion Paper Series in Economics ; No. 30-2021

Klassifikation
Wirtschaft
Neural Networks and Related Topics
Forecasting Models; Simulation Methods
Monetary Policy
Economic Sociology; Economic Anthropology; Language; Social and Economic Stratification
Thema
Word Embedding
Neural Network
Central Bank Communication
Natural Language Processing
Transfer Learning

Ereignis
Geistige Schöpfung
(wer)
Baumgärtner, Martin
Zahner, Johannes
Ereignis
Veröffentlichung
(wer)
Philipps-University Marburg, School of Business and Economics
(wo)
Marburg
(wann)
2021

Handle
Letzte Aktualisierung
10.03.2025, 11:42 MEZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Objekttyp

  • Arbeitspapier

Beteiligte

  • Baumgärtner, Martin
  • Zahner, Johannes
  • Philipps-University Marburg, School of Business and Economics

Entstanden

  • 2021

Ähnliche Objekte (12)