# A Tutorial on Deep Latent Variable Models of Natural Language

arXiv: https://arxiv.org/abs/1812.06834 · HTML: https://mlsanity.com/paper/1812.06834/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2018.

## Built on by (most cited first, 10 of 10)

- [PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model](https://mlsanity.com/paper/2306.02531/) (2023)
- [BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition](https://mlsanity.com/paper/2105.12848/) (2021)
- [A Survey to Recent Progress Towards Understanding In-Context Learning](https://mlsanity.com/paper/2402.02212/) (2024)
- [To be Closer: Learning to Link up Aspects with Opinions](https://mlsanity.com/paper/2109.08382/) (2021)
- [Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums](https://mlsanity.com/paper/2104.12643/) (2021)
- [An Overview on Controllable Text Generation via Variational Auto-Encoders](https://mlsanity.com/paper/2211.07954/) (2022)
- [Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation](https://mlsanity.com/paper/2301.02275/) (2023)
- [Indeterminate Probability Theory](https://mlsanity.com/paper/2303.11536/) (2023)
- [Continuous Indeterminate Probability Neural Network](https://mlsanity.com/paper/2303.12964/) (2023)
- [Unsupervised Learning of Harmonic Analysis Based on Neural HSMM with Code Quality Templates](https://mlsanity.com/paper/2403.04135/) (2024)

## Abstract (arXiv)

There has been much recent, exciting work on combining the complementary strengths of latent variable models and deep learning. Latent variable modeling makes it easy to explicitly specify model constraints through conditional independence properties, while deep learning makes it possible to parameterize these conditional likelihoods with powerful function approximators. While these "deep latent variable" models provide a rich, flexible framework for modeling many real-world phenomena, difficulties exist: deep parameterizations of conditional likelihoods usually make posterior inference intractable, and latent variable objectives often complicate backpropagation by introducing points of non-differentiability. This tutorial explores these issues in depth through the lens of variational inference.