Loading...

Text Summarization Using Deep Neural Networks

Sarkhani, Saeedeh | 2022

127 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55668 (31)
  4. University: Sharif University of Technology
  5. Department: Languages and Linguistics Center
  6. Advisor(s): Sameti, Hossein
  7. Abstract:
  8. In recent years, deep neural networks have achieved significant improvements in the field of automatic text summarization by using neural sequence architectures. However,the results of these improvements are more tangible in the production of short summaries (a few words or single sentences). In the field of producing long (multisentence) abstracts, the presented models suffer from several issues; These models produce the details of the events incorrectly and tend to generate the phrases been produced before repeatedly. The wording from the output of these models is very close to the original text. Also, the metrics used to evaluate the quality of produced summaries do not have the ability to determine the abstractive power of them. In this research, we utilize a model that strengthens the standard sequence-to-sequence model with the attention mechanism via using a pointer generator model to copy words from the source text to help reproducing information correctly. At the same time, it includes the ability to generate new words through the generator. A coverage mechanism is then used to keep track of the summarized episodes to avoid unnecessary repetition. Furthermore, we made use of a text-to-text transfer transformer model to rewrite the summary, which helps to improve the abstraction of the desired text, hence evaluating the quality of the obtained summaries in a multi-reference manner would be feasible. This model is applied to the augmented CNN/Daily Mail data and outperformed the baseline attention model by scoring 39.8 for ROUGE-1, 19.7 for ROUGE-2 and 36.9 for ROUGE-L
  9. Keywords:
  10. Abstractive Summarization ; Deep Neural Networks ; Attention Mechanism ; Text-to-Text Transfer Transformer ; Pointer Generator ; Coverage Mechanism ; Encoder-Decoder

 Digital Object List

 Bookmark

No TOC