Abstractive Arabic Text Summarization Based on Deep Learning.

Y.M Wazery,Abdelmgeid A Ali,Abdullah Alharbi,Marwa E Saleh,Ahmed Mostafa Khalil

doi:10.1155/2022/1566890

Y.M Wazery, Abdelmgeid A Ali + Show 3 more

Open Access

https://doi.org/10.1155/2022/1566890

Copy DOI

Abstract

Text summarization (TS) is considered one of the most difficult tasks in natural language processing (NLP). It is one of the most important challenges that stand against the modern computer system's capabilities with all its new improvement. Many papers and research studies address this task in literature but are being carried out in extractive summarization, and few of them are being carried out in abstractive summarization, especially in the Arabic language due to its complexity. In this paper, an abstractive Arabic text summarization system is proposed, based on a sequence-to-sequence model. This model works through two components, encoder and decoder. Our aim is to develop the sequence-to-sequence model using several deep artificial neural networks to investigate which of them achieves the best performance. Different layers of Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Bidirectional Long Short-Term Memory (BiLSTM) have been used to develop the encoder and the decoder. In addition, the global attention mechanism has been used because it provides better results than the local attention mechanism. Furthermore, AraBERT preprocess has been applied in the data preprocessing stage that helps the model to understand the Arabic words and achieves state-of-the-art results. Moreover, a comparison between the skip-gram and the continuous bag of words (CBOW) word2Vec word embedding models has been made. We have built these models using the Keras library and run-on Google Colab Jupiter notebook to run seamlessly. Finally, the proposed system is evaluated through ROUGE-1, ROUGE-2, ROUGE-L, and BLEU evaluation metrics. The experimental results show that three layers of BiLSTM hidden states at the encoder achieve the best performance. In addition, our proposed system outperforms the other latest research studies. Also, the results show that abstractive summarization models that use the skip-gram word2Vec model outperform the models that use the CBOW word2Vec model.

Highlights

ObjectivesOur aim is to develop the sequence-to-sequence model using several deep artificial neural networks to investigate which of them achieves the best performance
We found that that three layers of BiLSTM hidden states at the encoder achieve the best performance. e second direction is the way of preprocessing data and we found that the AraBERT preprocess has played an essential role in achieving the best performance. e third direction is the word embedding model that is used and the results showed that the skip-gram word2vec generated better summary quality than the CBOW word2vec model
We are looking forward to applying reinforcement learning algorithms and combining reinforcement learning techniques with deep learning models to improve the quality of the generated summary

Summary

Objectives

Our aim is to develop the sequence-to-sequence model using several deep artificial neural networks to investigate which of them achieves the best performance. Our aim was of developing the sequence-to-sequence model using several deep artificial neural networks to investigate which of them achieves the best performance

Methods

Results

Discussion

Conclusion