DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation

By Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya, Alexander Gelbukh. Conference on Empirical Methods in Natural Language Processing, 2019

678 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/dd20f00b0121075d2373e60025d59d9bddf89ea1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis (2021, background): “The former only tunes the parameters based on back-propagated gradients from the task loss (Zadeh et al., 2017; Tsai et al., 2019a; Ghosal et al., 2019), reconstruction loss (Mai et al., 2020), or auxiliary task loss (Chen et al., 2017; Yu et al., 2021).”
KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis (2020, methodology): “With the advent of graph neural networks, graph-based methods have become a new trend (Ghosal et al., 2019) in diverse NLP tasks such as emotion recogni-”
DynaEval: Unifying Turn and Dialogue Level Evaluation (2021, background): “Edge Relations Following (Ghosal et al., 2019), there are two aspects to take into account when deﬁning the relation types.”
Directed Acyclic Graph Network for Conversational Emotion Recognition (2021, methodology): “Empirical evidence also shows that a good representation of conversation context signiﬁcantly contributes to the model performance, especially when the content of query utterance is too short to be identiﬁed alone (Ghosal et al., 2019).”
COSMIC: COmmonSense knowledge for eMotion Identification in Conversations (2020, background): “With the growing popularity of conversational AI research, the topic of emotion recognition in conversations has received significant attention from the research community (Li et al., 2020; Ghosal et al., 2019; Zhang et al., 2019).”
MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation (2021, methodology): “Ghosal et al.(Ghosal et al., 2019), therefore, ﬁrst propose the DialogueGCN model which applies graph convolutional network (GCN) to capture long-distance contextual information in a conversation.”
A Survey on Vision--Language--Action Models for Embodied AI (2024, neutral): “Sentence-level graphs can be useful in dialog tracking [331], fact checking [332], etc. Document-level graphs include knowledge graphs [333], Table VIII: Vision-language models.”