← Back to papers
2018 ACL ACL 2018

EmotionX-AR: CNN-DCNN autoencoder based Emotion Classifier

Abstract

AbstractIn this paper, we model emotions in EmotionLines dataset using a convolutional-deconvolutional autoencoder (CNN-DCNN) framework. We show that adding a joint reconstruction loss improves performance. Quantitative evaluation with jointly trained network, augmented with linguistic features, reports best accuracies for emotion prediction; namely joy, sadness, anger, and neutral emotion in text.

🌉 Interdisciplinary Bridge — Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — convolutional autoencoder
🐝 Cross-Pollinator — Artificial Intelligence, Deep Learning, Machine Learning, Natural Language Processing, Speech & Audio

Authors

Sopan Khosla

Topics

Machine Learning > Learning Types > Self-Supervised Learning Deep Learning > Architectures > Autoencoders Natural Language Processing > Understanding > Sentiment Analysis Natural Language Processing > Applications > Text Classification Natural Language Processing > Applications > Sentiment Analysis Machine Learning > Learning Types > Classification Deep Learning > Learning Types > Representation Learning

Keywords

representation learning sentiment analysis text classification emotion recognition convolutional neural network emotion classification convolutional autoencoder deconvolutional network joint reconstruction linguistic feature text emotion
Download PDF

Related papers

Economic Event Detection in Company-Specific News Text 2018
Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus 2018
SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment 2018
Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer 2018
Affordances in Grounded Language Learning 2018