Can you tell? SSNet -- a Sagittal Stratum-inspired Neural Network Framework for Sentiment Analysis

Abstract

When people try to understand nuanced language they typically process multiple input sensor modalities to complete this cognitive task. It turns out the human brain has even a specialized neuron formation, called sagittal stratum, to help us understand sarcasm. We use this biological formation as the inspiration for designing a neural network architecture that combines predictions of different models on the same text to construct robust, accurate and computationally efficient classifiers for sentiment analysis and study several different realizations. Among them, we propose a systematic new approach to combining multiple predictions based on a dedicated neural network and develop mathematical analysis of it along with state-of-the-art experimental results. We also propose a heuristic-hybrid technique for combining models and back it up with experimental results on a representative benchmark dataset and comparisons to other methods to show the advantages of the new approaches.

23 pages, 4 figures, 5 tables, 42 references

References in corpus (7)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Popular Ensemble Methods: An Empirical Study
• Universal Sentence Encoder
• Underspecification Presents Challenges for Credibility in Modern Machine Learning
• Deep Learning Based Text Classification: A Comprehensive Review
• Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence
• BowTie - A deep learning feedforward neural network for sentiment analysis