# Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation

arXiv: https://arxiv.org/abs/2104.08857 · HTML: https://mlsanity.com/paper/2104.08857/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [Adversarial Removal of Demographic Attributes from Text Data](https://mlsanity.com/paper/1808.06640/) (2018)
- [Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory](https://mlsanity.com/paper/1704.01074/) (2017)
- [Neural Responding Machine for Short-Text Conversation](https://mlsanity.com/paper/1503.02364/) (2015)
- [MojiTalk: Generating Emotional Responses at Scale](https://mlsanity.com/paper/1711.04090/) (2017)
- [Latent Variable Dialogue Models and their Diversity](https://mlsanity.com/paper/1702.05962/) (2017)
- [Condition-Transforming Variational AutoEncoder for Conversation Response Generation](https://mlsanity.com/paper/1904.10610/) (2019)

## Built on by (most cited first, 9 of 9)

- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [EEG2Vec: Learning Affective EEG Representations via Variational Autoencoders](https://mlsanity.com/paper/2207.08002/) (2022)
- [LLM-based multi-agent poetry generation in non-cooperative environments](https://mlsanity.com/paper/2409.03659/) (2024)
- [Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents](https://mlsanity.com/paper/2202.05971/) (2022)
- [CAB: Empathetic Dialogue Generation with Cognition, Affection and Behavior](https://mlsanity.com/paper/2302.01935/) (2023)
- [An Empirical Bayes Framework for Open-Domain Dialogue Generation](https://mlsanity.com/paper/2311.10945/) (2023)
- [A Review of Affective Generation Models](https://mlsanity.com/paper/2202.10763/) (2022)
- [Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights](https://mlsanity.com/paper/2407.11449/) (2024)
- [Partially Randomizing Transformer Weights for Dialogue Response Diversity](https://mlsanity.com/paper/2311.10943/) (2023)

## Abstract (arXiv)

This paper presents an emotion-regularized conditional variational autoencoder (Emo-CVAE) model for generating emotional conversation responses. In conventional CVAE-based emotional response generation, emotion labels are simply used as additional conditions in prior, posterior and decoder networks. Considering that emotion styles are naturally entangled with semantic contents in the language space, the Emo-CVAE model utilizes emotion labels to regularize the CVAE latent space by introducing an extra emotion prediction network. In the training stage, the estimated latent variables are required to predict the emotion labels and token sequences of the input responses simultaneously. Experimental results show that our Emo-CVAE model can learn a more informative and structured latent space than a conventional CVAE model and output responses with better content and emotion performance than baseline CVAE and sequence-to-sequence (Seq2Seq) models.