T. Mazzocco
Sentic neural networks: A novel cognitive model for affective common sense reasoning
Mazzocco, T.; Cambria, E.; Hussain, A.; Wang, Q.-F.
Abstract
In human cognition, the capacity to reason and make decisions is strictly dependent on our common sense knowledge about the world and our inner emotional states: we call this ability affective common sense reasoning. In previous works, graph mining and multi-dimensionality reduction techniques have been employed in attempt to emulate such a process and, hence, to semantically and affectively analyze natural language text. In this work, we exploit a novel cognitive model based on the combined use of principal component analysis and artificial neural networks to perform reasoning on a knowledge base obtained by merging a graph representation of common sense with a linguistic resource for the lexical representation of affect. Results show a noticeable improvement in emotion recognition from natural language text and pave the way for more bio-inspired approaches to the emulation of affective common sense reasoning.
Citation
Mazzocco, T., Cambria, E., Hussain, A., & Wang, Q.-F. (2012, July). Sentic neural networks: A novel cognitive model for affective common sense reasoning. Presented at BICS: International Conference on Brain Inspired Cognitive Systems, Shenyang, China
Presentation Conference Type | Conference Paper (published) |
---|---|
Conference Name | BICS: International Conference on Brain Inspired Cognitive Systems |
Start Date | Jul 11, 2012 |
End Date | Jul 14, 2012 |
Publication Date | 2012 |
Deposit Date | Oct 17, 2019 |
Publisher | Springer |
Pages | 12-21 |
Series Title | Lecture Notes in Computer Science |
Series Number | 7366 |
Series ISSN | 0302-9743 |
Book Title | Advances in Brain Inspired Cognitive Systems |
ISBN | 978-3-642-31560-2 |
DOI | https://doi.org/10.1007/978-3-642-31561-9_2 |
Keywords | AI, NLP, Neural Networks, Cognitive Modeling, Sentic Computing |
Public URL | http://researchrepository.napier.ac.uk/Output/1793270 |
You might also like
MA-Net: Resource-efficient multi-attentional network for end-to-end speech enhancement
(2024)
Journal Article
Artificial intelligence enabled smart mask for speech recognition for future hearing devices
(2024)
Journal Article
Are Foundation Models the Next-Generation Social Media Content Moderators?
(2024)
Journal Article