Loading...

Named Entity Recognition in Persian Language Using Deep Learning

Aghajani, Mohammad Mahdi | 2021

861 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54174 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Beigy, Hamid
  7. Abstract:
  8. The use of named entity recognition systems as preprocessing is used in many natural language analysis issues. With the advent of deep learning, the methods of this area were also affected. Today, there is considerable progress in this area due to the development of data resources for English, Chinese, German, and Spanish. They are also good trained models in formal Persian. However, for informal Persian, which contains a large portion of the web content under the Web, the current models do not produce a suitable solution. In this study, we use the same approach to train our models due to achieving state-of-the-art results in pre-trained models. On the other hand, there is a lack of standard datasets for informal Persian in this area. In this study, first, datasets were prepared and produced from Persian Twitter data according to standard and official procedures. Then, Persian models have been tested on the dataset, and it has been determined that they have no acceptable quality. Then, using transfer learning and parallel learning, improve the f-score from 65 to 82. In this study, using a tool that was developed for representation visualization of different layers of the network, it was found that current models for the problem of named entity recognition are more than paying attention to content themselves rather than context, which can be a clue to improve current models in the future
  9. Keywords:
  10. Pretrained Models ; Transfer Learning ; Natural Language Processing ; Deep Learning ; Multi-Task Learning ; Named Entity Recognition

 Digital Object List

 Bookmark

...see more