Feature pyramid with attention fusion for edge discontinuity classification

Optimisation of CNN Through Transferable Online Knowledge for Stress and Sentiment Classification

“…Recursive Auto-Encoders (RAE): RAE is a neural network model used in natural language processing (NLP) to learn hierarchical representations of sentences or other sequential data. RAEs are particularly effective for capturing the syntactic structure of sentences and have applications in tasks such as parsing, sentiment analysis, and machine translation [47].…”