Please use this identifier to cite or link to this item:
Title: Monetary policy information extraction from open sources based on deep neural networks and natural language processing
Authors: Xue, Zixian
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Electrical and electronic engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Xue, Z. (2022). Monetary policy information extraction from open sources based on deep neural networks and natural language processing. Master's thesis, Nanyang Technological University, Singapore.
Abstract: With the process of economic globalization, state agencies, enterprises and individuals are paying more and more attention to the monetary policies of other countries. The Internet is the main source of relevant information, but the information on it is numerous and complex. Extracting information from monetary policy news can save a lot of time and improve the efficiency of decision-making. This dissertation first investigates the main techniques for accomplishing NLP tasks in chronological order. The dataset is then customized by web crawlers according to the characteristics of monetary policy news. And the self-collected dataset is preprocessed to facilitate downstream tasks. Then, a text classification model based on deep learning is studied for the self-collected dataset. The tuning optimization process of the main hyperparameters in the model is analyzed to explain their effects. Finally, the optimized TextRank model is applied to the self-collected dataset and compared with generative summarization techniques.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Monetary Policy Information Extraction from Open Sources Based on Deep Neural Networks and Natural Language Processing.pdf
  Restricted Access
6.83 MBAdobe PDFView/Open

Page view(s)

Updated on May 16, 2022


Updated on May 16, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.