DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation (2019-08-01T00:00:00.000000Z)

TL;DR

Through the graph network, DialogueGCN addresses context propagation issues present in the current RNN-based methods, and empirically show that this method alleviates such issues, while outperforming the current state of the art on a number of benchmark emotion classification datasets.

Abstract

Emotion recognition in conversation (ERC) has received much attention, lately, from researchers due to its potential widespread applications in diverse areas, such as health-care, education, and human resources. In this paper, we present Dialogue Graph Convolutional Network (DialogueGCN), a graph neural network based approach to ERC. We leverage self and inter-speaker dependency of the interlocutors to model conversational context for emotion recognition. Through the graph network, DialogueGCN addresses context propagation issues present in the current RNN-based methods. We empirically show that this method alleviates such issues, while outperforming the current state of the art on a number of benchmark emotion classification datasets.

Authors

Soujanya Poria

37 papers

Navonil Majumder

18 papers

Deepanway Ghosal

12 papers

TL;DR

Abstract

Authors

References35 items

Emotion Recognition on Twitter: Comparative Study and Training a Unison Model

Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances

ANA at SemEval-2019 Task 3: Contextual Emotion detection in Conversations through hierarchical LSTMs and BERT

DialogueRNN: An Attentive RNN for Emotion Detection in Conversations

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations

Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos

Decision support with text-based emotion recognition: Deep learning for affective computing

Memory Fusion Network for Multi-view Sequential Learning

EmotionLines: An Emotion Corpus of Multi-Party Conversations

Multi-attention Recurrent Network for Human Communication Comprehension

Multimodal sentiment analysis with word-level fusion and reinforcement learning

Context-Dependent Sentiment Analysis in User-Generated Videos

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

Neural Message Passing for Quantum Chemistry

Modeling Relational Data with Graph Convolutional Networks

Quasi-Recurrent Neural Networks

Semi-Supervised Classification with Graph Convolutional Networks

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Mirroring Facial Expressions and Emotions in Dyadic Conversations

End-To-End Memory Networks

Adam: A Method for Stochastic Optimization

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

GloVe: Global Vectors for Word Representation

Convolutional Neural Networks for Sentence Classification

Spectral Networks and Locally Connected Networks on Graphs

AVEC 2012: the continuous audio/visual emotion challenge

Annotating and Identifying Emotions in Text

Rectified Linear Units Improve Restricted Boltzmann Machines

IEMOCAP: interactive emotional dyadic motion capture database

Predicting Affective States expressed through an Emote-Aloud Procedure from AutoTutor's Mixed-Initiative Dialogue

Long Short-Term Memory

ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection

Soujanya Poria, Erik Cambria, and Louis-Philippe Morency

The Graph Neural Network Model

This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING

Field of Study

Venue Information

Name

Type

URL

Alternate Names