DAMIAN – data accrual machine intelligence with augmented networks for contextually coherent creative story generation
by B.J. Sowmya; D. Pradeep Kumar; R. Hanumantharaju; K.G. Srinivasa
International Journal of Business Intelligence and Data Mining (IJBIDM), Vol. 22, No. 1/2, 2023

Abstract: Cognitive computing refers to the usage of computer models to simulate human intelligence and thought process in a complex situation. Artificial intelligence (AI) is an augmentation to the limits of human capacity for a particular domain and works as an absolute reflection of reality. AI is where a computer program is able to efficiently make decisions without previous explicit knowledge and instruction. The concept of cognitive intelligence was introduced. The most interesting use case for this would be an AI bot that doubles as a digital assistant. This is aimed at solving core problems in AI like open domain question answering, context understanding, aspect-based sentiment analysis, text generation, etc. The work presents a model to develop a multi-resolution RNN to identify local and global context, develop contextual embedding via transformers to pass into a seq2seq architecture and add heavy regularisation and augment data with reinforcement learning, and optimise via recursive neural networks.

Online publication date: Wed, 30-Nov-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Business Intelligence and Data Mining (IJBIDM):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com