conftrace_

2018 EMNLP EMNLP 2018

EmotiKLUE at IEST 2018: Topic-Informed Classification of Implicit Emotions

Abstract

AbstractEmotiKLUE is a submission to the Implicit Emotion Shared Task. It is a deep learning system that combines independent representations of the left and right contexts of the emotion word with the topic distribution of an LDA topic model. EmotiKLUE achieves a macro average F₁score of 67.13%, significantly outperforming the baseline produced by a simple ML classifier. Further enhancements after the evaluation period lead to an improved F₁score of 68.10%.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Thomas Proisl, Philipp Heinrich, Besim Kabashi, Stefan Evert

Topics

Machine Learning > Core Methods > Classification Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Neural Networks Natural Language Processing > Applications > Sentiment Analysis Deep Learning > Learning Types > Representation Learning Machine Learning > Core Methods > Topic Modeling

Keywords

latent dirichlet allocation deep learning topic model sentence embedding implicit emotion classification

More from EMNLP 2018

All EMNLP 2018 papers →

NL-FIIT at IEST-2018: Emotion Recognition utilizing Neural Networks and Multi-level Preprocessing

UWB at IEST 2018: Emotion Prediction in Tweets with Bidirectional Long Short-Term Memory Neural Network

USI-IR at IEST 2018: Sequence Modeling and Pseudo-Relevance Feedback for Implicit Emotion Detection

BrainT at IEST 2018: Fine-tuning Multiclass Perceptron For Implicit Emotion Classification

Disney at IEST 2018: Predicting Emotions using an Ensemble

Sentylic at IEST 2018: Gated Recurrent Neural Network and Capsule Network Based Approach for Implicit Emotion Detection