Design of an Automated Summarization Model Using Convolutional Graph Based Network

The summarization of the text has emerged as an essential technique for managing the ever-expanding vast amount of digital data, enhancing effectiveness across diverse domains, for example, healthcare, law, education, and journalism. By addressing the challenge of data saturation, summarization methods compress comprehensive documents into shorter, informative representations that improve decision-making, broaden accessibility, and save time. Ongoing advancements in neural architectures and language models have accelerated research in this field with research article summarization moving beyond earlier extractive strategies toward advanced abstractive models, alongside recent innovations in multimodal summarization. To explore the evolution of this discipline, the present study proposes Convolutional Graph Based Text Summarization Network model (CGTSNet), drawing on data from the SurveySum and MS² dataset. As well as bibliometric and critical evaluations are employed to propose CGTSNet future directions for the field. On the whole, this investigation not only illustrates the progress accomplished but also serves as a foundation for guiding future research and fostering innovation in the rapidly evolving area of document summarization.