# Variational Transformers for Diverse Response Generation

arXiv: https://arxiv.org/abs/2003.12738 · HTML: https://mlsanity.com/paper/2003.12738/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2020.

## Built on by (most cited first, 30 of 36)

- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TransDreamer: Reinforcement Learning with Transformer World Models](https://mlsanity.com/paper/2202.09481/) (2022)
- [Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction](https://mlsanity.com/paper/2104.00563/) (2021)
- [Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling](https://mlsanity.com/paper/2207.04179/) (2022)
- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)
- [Transformer-based Conditional Variational Autoencoder for Controllable Story Generation](https://mlsanity.com/paper/2101.00828/) (2021)
- [Diffusion-based Document Layout Generation](https://mlsanity.com/paper/2303.10787/) (2023)
- [Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation](https://mlsanity.com/paper/2207.06130/) (2022)
- [Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization](https://mlsanity.com/paper/2109.06471/) (2021)
- [Guiding Visual Question Generation](https://mlsanity.com/paper/2110.08226/) (2021)
- [Exploiting Pretrained Biochemical Language Models for Targeted Drug Design](https://mlsanity.com/paper/2209.00981/) (2022)
- [Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design](https://mlsanity.com/paper/2205.13927/) (2022)
- [PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism](https://mlsanity.com/paper/2212.09086/) (2022)
- [CAB: Empathetic Dialogue Generation with Cognition, Affection and Behavior](https://mlsanity.com/paper/2302.01935/) (2023)
- [Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables](https://mlsanity.com/paper/2212.01145/) (2022)
- [An Empirical Bayes Framework for Open-Domain Dialogue Generation](https://mlsanity.com/paper/2311.10945/) (2023)
- [RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning](https://mlsanity.com/paper/2205.10857/) (2022)
- [Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation](https://mlsanity.com/paper/2109.07779/) (2021)
- [Learning Speaker-specific Lip-to-Speech Generation](https://mlsanity.com/paper/2206.02050/) (2022)
- [A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck](https://mlsanity.com/paper/2207.13529/) (2022)
- [Learning Interpretable Latent Dialogue Actions With Less Supervision](https://mlsanity.com/paper/2209.11128/) (2022)
- [Effective Transfer Learning for Low-Resource Natural Language Understanding](https://mlsanity.com/paper/2208.09180/) (2022)
- [Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation](https://mlsanity.com/paper/2210.12409/) (2022)
- [Partially Randomizing Transformer Weights for Dialogue Response Diversity](https://mlsanity.com/paper/2311.10943/) (2023)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)
- [Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models](https://mlsanity.com/paper/2505.09062/) (2025)
- [WakaVT: A Sequential Variational Transformer for Waka Generation](https://mlsanity.com/paper/2104.00426/) (2021)
- [SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis](https://mlsanity.com/paper/2108.02572/) (2021)
- [VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search](https://mlsanity.com/paper/2108.02725/) (2021)
- [Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation](https://mlsanity.com/paper/2109.05778/) (2021)

## Abstract (arXiv)

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work proposes to capture the variability of dialogue responses with a recurrent neural network (RNN)-based conditional variational autoencoder (CVAE). However, the autoregressive computation of the RNN limits the training efficiency. Therefore, we propose the Variational Transformer (VT), a variational self-attentive feed-forward sequence model. The VT combines the parallelizability and global receptive field of the Transformer with the variational nature of the CVAE by incorporating stochastic latent variables into Transformers. We explore two types of the VT: 1) modeling the discourse-level diversity with a global latent variable; and 2) augmenting the Transformer decoder with a sequence of fine-grained latent variables. Then, the proposed models are evaluated on three conversational datasets with both automatic metric and human evaluation. The experimental results show that our models improve standard Transformers and other baselines in terms of diversity, semantic relevance, and human judgment.