Abstract
Dealing with vast amounts of textual data requires the use of efficient systems. Automatic summarization systems are capable of addressing this issue. Therefore, it becomes highly essential to work on the design of existing automatic summarization systems and innovate them to make them capable of meeting the demands of continuously increasing data, based on user needs. This study tends to survey the scientific literature to obtain information and knowledge about the recent research in automatic text summarization specifically abstractive summarization based on neural networks. A review of various neural networks based abstractive summarization models have been presented. The proposed conceptual framework includes five key elements identified as encoder-decoder architecture, mechanisms, training strategies and optimization algorithms, dataset, and evaluation metric. A description of these elements is also included in this article. The purpose of this research is to provide an overall understanding and familiarity with the elements of recent neural networks based abstractive text summarization models with an up-to-date review as well as to render an awareness of the challenges and issues with these systems. Analysis has been performed qualitatively with the help of a concept matrix indicating common trends in the design of recent neural abstractive summarization systems. Models employing a transformer-based encoder-decoder architecture are found to be the new state-of-the-art. Based on the knowledge acquired from the survey, this article suggests the use of pre-trained language models in complement with neural network architecture for abstractive summarization task.
Highlights
In the present technological era, there is a significant increase in textual data in digital form and it is continuously multiplying
This article presents an up-to-date review of abstractive text summarization by surveying related scientific literature
A research framework is created in line with the key design elements like encoder-decoder architecture, mechanisms, training and optimization methods, datasets, and evaluation metric for the abstractive summarization models and is analyzed with the help of the concept matrix highlighting the common design trends of the recent abstractive summarization systems
Summary
In the present technological era, there is a significant increase in textual data in digital form and it is continuously multiplying. Prior research on automatic summarization systems highlighted certain challenges such as the need for intelligent systems that can analyze a language and understand its semantics at a deeper level as well as generate purposeful sentences/descriptions from input data like human language [3]. Three pipelined tasks are at the core of abstractive summarization approaches [5]: information extraction, content selection, and surface realization. Semantic-based methods work on identifying noun and verb phrases by applying linguistic/semantic illustration of a text document as an input to the natural language generation system. These systems include multimodal semantic-based techniques, information item-based methods, semantic text representation, and semantic graph methods [13], [14]. There are several advancements in text summarization using the concepts and methods of deep learning where sequence to sequence models are known to be the foundation of most of the recent studies [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
