Abstractive text summarization using deep learning models: a survey

doi:10.1007/s41060-025-00743-w

Abstractive text summarization using deep learning models: a survey

2025-03-01

0

PRE

AI

M

Mustafa Abdul Salam *

DOI：10.1007/s41060-025-00743-w

Original

Original request for help

Save

Abstract

En 中文

In the face of escalating volumes of textual data, the demand for advanced systems to efficiently manage this deluge is evident. Automatic summarization is a pivotal solution, continually evolving to meet the burgeoning data needs and user expectations. This paper delves into abstract text summarization, particularly focusing on utilizing neural networks-a recent breakthrough in the field. Through a comprehensive analysis of various models, we meticulously dissect critical components such as encoder-decoder design, mechanisms, training methodologies, dataset considerations, and evaluation metrics. Our primary objective is to illuminate current model landscapes, pinpoint existing challenges, and propose potential remedies. Notably, transformer-based encoder-decoder architectures emerge as state-of-the-art solutions. We suggest combining neural networks with pre-trained language models to improve abstractive summarization, making advanced techniques more accessible and effective. This approach aims to bolster the efficiency and efficacy of summarization systems, thereby facilitating superior information extraction and comprehension for users grappling with extensive textual datasets.

Keywords:

NLP

Abstract text summarization

Encoder-decoder

Mechanism attention

Transformers

Abstractive text summarization using deep learning models: a survey

Abstract

Journal

Organization