Statistical Language Modeling for Historical Documents using Weighted Finite-State Transducers and Long Short-Term Memory

Doctoral thesis English OPEN
Al Azawi, Mayce;
  • Subject: weighted finite-state transducers | long short-term memory | artificial neural network | document analysis | historical documents | image processing | language modeling | optical character recognition
    • msc: msc:00-XX
      ddc: ddc:004

The goal of this work is to develop statistical natural language models and processing techniques based on Recurrent Neural Networks (RNN), especially the recently introduced Long Short- Term Memory (LSTM). Due to their adapting and predicting abilities, these met... View more
Share - Bookmark