KSU at SemEval-2019 Task 3: Hybrid Features for Emotion Recognition in Textual Conversation

Abstract

We proposed a model to address emotion recognition in textual conversation based on using automatically extracted features and human engineered features. The proposed model utilizes a fast gated-recurrent-unit backed by CuDNN, and a convolutional neural network to automatically extract features. The human engineered features take the frequency-inverse document frequency of semantic meaning and mood tags extracted from SinticNet.

Tasks

Reproductions