Overview / Usage

With the enormous growth rate in user-generated academic resources such as videos, audios, texts, courses; efficient navigation of these resources has become very important. To get a quick sense of the narratives, it will be useful to have summary with appropriate title of such resources. To generate these segments manually is not only a task of skill but also of specialized content knowledge. Leveraging capacity of machine learning and automation we can have intelligent systems to generate these with minimum human interference. We are proposing to generate it using text processing, NLP and machine learning techniques. After testing it on academic resources, it could be extended to apply in the publishing industry to generate abstracts and titles automatically for books, conference proceedings, research papers etc.

Methodology / Approach

Variants of Sequence Models, Language Models, Transformers Architecture