Deep Learning for Automatic Text Summarization
Youcef Ghibeche, Abdallah Sellam, Nabil Abdelkader Nouri, Saad Laggoun, Nizar Omar Idris Khadroun · 2024
In today's digital age, the rapid accumulation of textual information necessitates effective automatic text summarization. The demand for computer systems capable of summarizing vast amounts of information has grown exponentially, aiding users in extracting key insights and making informed decisions. This study focuses on the development of a robust abstractive text summarization model utilizing Deep Learning and Seq2Seq models with LSTM networks and attention mechanisms. Through the construction of a Seq2Seq-based framework incorporating LSTM layers and attention mechanisms, the model effectively captures semantic relationships and contextual dependencies within the input text. Training strategies, optimization techniques, and word embedding methods, including pretrained word embedding like GloVe, were employed to enhance the model's ability to generate accurate and concise summaries.