EmoAtt at EmoInt-2017: Inner attention sentence embedding for Emotion Intensity

TL;DR

This paper presents a deep learning model with inner attention for emotion intensity prediction, achieving competitive results without using lexicons in the WASSA 2017 shared task.

Contribution

It introduces an inner attention mechanism on top of RNNs for emotion intensity prediction, a novel approach in this context.

Findings

Achieved 13rd place among 22 competitors

Successfully identified emotion-bearing words without lexicons

Demonstrated effective representation learning for emotion intensity

Abstract

In this paper we describe a deep learning system that has been designed and built for the WASSA 2017 Emotion Intensity Shared Task. We introduce a representation learning approach based on inner attention on top of an RNN. Results show that our model offers good capabilities and is able to successfully identify emotion-bearing words to predict intensity without leveraging on lexicons, obtaining the 13th place among 22 shared task competitors.