# Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation

arXiv: https://arxiv.org/abs/2011.01136 · HTML: https://mlsanity.com/paper/2011.01136/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

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

- [You Are What You Write: Preserving Privacy in the Era of Large Language Models](https://mlsanity.com/paper/2204.09391/) (2022)
- [Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers](https://mlsanity.com/paper/2103.16289/) (2021)
- [Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information](https://mlsanity.com/paper/2305.16967/) (2023)
- [Affective Decoding for Empathetic Response Generation](https://mlsanity.com/paper/2108.08102/) (2021)
- [Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs](https://mlsanity.com/paper/2209.12590/) (2022)
- [Improving Variational Autoencoders with Density Gap-based Regularization](https://mlsanity.com/paper/2211.00321/) (2022)
- [Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation](https://mlsanity.com/paper/2210.12409/) (2022)
- [PUF-Phenotype: A Robust and Noise-Resilient Approach to Aid Intra-Group-based Authentication with DRAM-PUFs Using Machine Learning](https://mlsanity.com/paper/2207.04692/) (2022)
- [Requirement Formalisation using Natural Language Processing and Machine Learning: A Systematic Review](https://mlsanity.com/paper/2303.13365/) (2023)

## Abstract (arXiv)

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling, where the approximate posterior collapses to the prior, and the model will totally ignore the latent variables and be degraded to a plain language model during text generation. Such an issue is particularly prevalent when RNN-based VAE models are employed for text modelling. In this paper, we propose a simple, generic architecture called Timestep-Wise Regularisation VAE (TWR-VAE), which can effectively avoid posterior collapse and can be applied to any RNN-based VAE models. The effectiveness and versatility of our model are demonstrated in different tasks, including language modelling and dialogue response generation.