A model for abstractive summarization of scientific papers methodology

• Grant number: 21/12389-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): December 01, 2021
• Effective date (End): November 30, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Paulo Sergio Silva Rodrigues
• Grantee: Weverson da Silva Pereira
• Host Institution: Campus de São Bernardo do Campo. Centro Universitário da FEI (UNIFEI). Fundação Educacional Inaciana Padre Sabóia de Medeiros (FEI). São Bernardo do Campo , SP, Brazil

Abstract

Currently, there are many scientific papers available online, which has led to a considerable advance in science as a whole, providing more opportunities for collaboration and sharing of this type of information among researchers. Sites like Semantic Scholar ArXiv and Google Scholar are examples of free platforms for immediate access. Furthermore, paid platforms such as IEEE Xplore and Science Direct also present immense knowledge to humanity. However, although the generation of all this available knowledge is favorable to the scientific-technological development of humanity, on the other hand, its organization becomes a challenge never before imagined. One of these challenges is the analysis of an ever-increasing amount of information. A common way among researchers to analyze scientific publications is to segment them into objectives, problem-solving methods, results obtained, and future work. It is a process that, if done manually, becomes quite costly in terms of time and tedious for those who are analyzing. On the other hand, natural language processing has also evolved a lot, especially in recent decades, due to the advancement of hardware, which allowed the processing and statistical analysis of large amounts of data. Thus, this project aims to present a methodology based on modern machine learning techniques for academic-scientific articles segmentation in the technological area, which semantically describes the methodology, one of the four segments mentioned here.(AU)