# Conditional Variational Autoencoder for Neural Machine Translation

arXiv: https://arxiv.org/abs/1812.04405 · HTML: https://mlsanity.com/paper/1812.04405/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2018.

## Built on by (most cited first, 20 of 20)

- [Conditional Variational Capsule Network for Open Set Recognition](https://mlsanity.com/paper/2104.09159/) (2021)
- [Counterfactual Generative Models for Time-Varying Treatments](https://mlsanity.com/paper/2305.15742/) (2023)
- [GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents](https://mlsanity.com/paper/2412.10410/) (2024)
- [Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translation](https://mlsanity.com/paper/2302.09368/) (2023)
- [ReliCD: A Reliable Cognitive Diagnosis Framework with Confidence Awareness](https://mlsanity.com/paper/2401.10749/) (2023)
- [Hypergraph-based Motion Generation with Multi-modal Interaction Relational Reasoning](https://mlsanity.com/paper/2409.11676/) (2024)
- [INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations](https://mlsanity.com/paper/2209.01061/) (2022)
- [Target-Side Augmentation for Document-Level Machine Translation](https://mlsanity.com/paper/2305.04505/) (2023)
- [Regularizing Transformers With Deep Probabilistic Layers](https://mlsanity.com/paper/2108.10764/) (2021)
- [A Joint Learning Model with Variational Interaction for Multilingual Program Translation](https://mlsanity.com/paper/2408.14515/) (2024)
- [Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables](https://mlsanity.com/paper/2208.05482/) (2022)
- [Evaluating Generative Vehicle Trajectory Models for Traffic Intersection Dynamics](https://mlsanity.com/paper/2506.08963/) (2025)
- [Deep Limit Model-free Prediction in Regression](https://mlsanity.com/paper/2408.09532/) (2024)
- [Deep Learning Models in Software Requirements Engineering](https://mlsanity.com/paper/2105.07771/) (2021)
- [Generating Diverse Descriptions from Semantic Graphs](https://mlsanity.com/paper/2108.05659/) (2021)
- [BGaitR-Net: Occluded Gait Sequence reconstructionwith temporally constrained model for gait recognition](https://mlsanity.com/paper/2110.09564/) (2021)
- [Variational Autoencoders for Precoding Matrices with High Spectral Efficiency](https://mlsanity.com/paper/2111.15626/) (2021)
- [Pluvio: Assembly Clone Search for Out-of-domain Architectures and Libraries through Transfer Learning and Conditional Variational Information Bottleneck](https://mlsanity.com/paper/2307.10631/) (2023)
- [DiffuMural: Restoring Dunhuang Murals with Multi-scale Diffusion](https://mlsanity.com/paper/2504.09513/) (2025)
- [Assessing Low Back Movement with Motion Tape Sensor Data Through Deep Learning](https://mlsanity.com/paper/2602.11465/) (2026)

## Abstract (arXiv)

We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent variable to model features of the translation process. We extend this model with a co-attention mechanism motivated by Parikh et al. in the inference network. Compared to the vision domain, latent variable models for text face additional challenges due to the discrete nature of language, namely posterior collapse. We experiment with different approaches to mitigate this issue. We show that our conditional variational model improves upon both discriminative attention-based translation and the variational baseline presented in Zhang et al. Finally, we present some exploration of the learned latent space to illustrate what the latent variable is capable of capturing. This is the first reported conditional variational model for text that meaningfully utilizes the latent variable without weakening the translation model.