# Disentangled Variational Autoencoder for Emotion Recognition in Conversations

arXiv: https://arxiv.org/abs/2305.14071 · HTML: https://mlsanity.com/paper/2305.14071/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 62 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [DialogueRNN: An Attentive RNN for Emotion Detection in Conversations](https://mlsanity.com/paper/1811.00405/) (2018)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [COSMIC: COmmonSense knowledge for eMotion Identification in Conversations](https://mlsanity.com/paper/2010.02795/) (2020)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances](https://mlsanity.com/paper/1905.02947/) (2019)
- [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://mlsanity.com/paper/2105.12907/) (2021)
- [Weakly Supervised Disentanglement with Guarantees](https://mlsanity.com/paper/1910.09772/) (2019)
- [DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition](https://mlsanity.com/paper/2012.08695/) (2020)
- [Generating Sentences from Disentangled Syntactic and Semantic Spaces](https://mlsanity.com/paper/1907.05789/) (2019)
- [Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection](https://mlsanity.com/paper/2106.01071/) (2021)
- [Improving Disentangled Text Representation Learning with Information-Theoretic Guidance](https://mlsanity.com/paper/2006.00693/) (2020)
- [Hierarchical Pre-training for Sequence Labelling in Spoken Dialog](https://mlsanity.com/paper/2009.11152/) (2020)
- [CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation](https://mlsanity.com/paper/2108.11626/) (2021)
- [Contrast and Generation Make BART a Good Dialogue Emotion Recognizer](https://mlsanity.com/paper/2112.11202/) (2021)
- [Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation](https://mlsanity.com/paper/2210.08713/) (2022)
- [Dimensional Emotion Detection from Categorical Emotion](https://mlsanity.com/paper/1911.02499/) (2019)
- [Weakly Supervised Disentanglement by Pairwise Similarities](https://mlsanity.com/paper/1906.01044/) (2019)

## Built on by (most cited first, 5 of 5)

- [EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector](https://mlsanity.com/paper/2411.02625/) (2024)
- [A Bipartite Graph is All We Need for Enhancing Emotional Reasoning with Commonsense Knowledge](https://mlsanity.com/paper/2308.04811/) (2023)
- [ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy](https://mlsanity.com/paper/2308.06450/) (2023)
- [Dynamic Causal Disentanglement Model for Dialogue Emotion Detection](https://mlsanity.com/paper/2309.06928/) (2023)
- [Disentangled VAD Representations via a Variational Framework for Political Stance Detection](https://mlsanity.com/paper/2502.19276/) (2025)

## Abstract (arXiv)

In Emotion Recognition in Conversations (ERC), the emotions of target utterances are closely dependent on their context. Therefore, existing works train the model to generate the response of the target utterance, which aims to recognise emotions leveraging contextual information. However, adjacent response generation ignores long-range dependencies and provides limited affective information in many cases. In addition, most ERC models learn a unified distributed representation for each utterance, which lacks interpretability and robustness. To address these issues, we propose a VAD-disentangled Variational AutoEncoder (VAD-VAE), which first introduces a target utterance reconstruction task based on Variational Autoencoder, then disentangles three affect representations Valence-Arousal-Dominance (VAD) from the latent space. We also enhance the disentangled representations by introducing VAD supervision signals from a sentiment lexicon and minimising the mutual information between VAD distributions. Experiments show that VAD-VAE outperforms the state-of-the-art model on two datasets. Further analysis proves the effectiveness of each proposed module and the quality of disentangled VAD representations. The code is available at https://github.com/SteveKGYang/VAD-VAE.