# A Hierarchical Latent Structure for Variational Conversation Modeling

arXiv: https://arxiv.org/abs/1804.03424 · HTML: https://mlsanity.com/paper/1804.03424/

## Key facts

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

## Built on by (most cited first, 17 of 17)

- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019)
- [Human-centric Dialog Training via Offline Reinforcement Learning](https://mlsanity.com/paper/2010.05848/) (2020)
- [Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection](https://mlsanity.com/paper/2106.01071/) (2021)
- [A Survey on Recent Advances in Conversational Data Generation](https://mlsanity.com/paper/2405.13003/) (2024)
- [A Variational Hierarchical Model for Neural Cross-Lingual Summarization](https://mlsanity.com/paper/2203.03820/) (2022)
- [GTM: A Generative Triple-Wise Model for Conversational Question Generation](https://mlsanity.com/paper/2106.03635/) (2021)
- [A Mixture-of-Expert Approach to RL-based Dialogue Management](https://mlsanity.com/paper/2206.00059/) (2022)
- [Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents](https://mlsanity.com/paper/2202.05971/) (2022)
- [LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing](https://mlsanity.com/paper/2105.01992/) (2021)
- [Modulating Language Models with Emotions](https://mlsanity.com/paper/2108.07886/) (2021)
- [Response-act Guided Reinforced Dialogue Generation for Mental Health Counseling](https://mlsanity.com/paper/2301.12729/) (2023)
- [PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism](https://mlsanity.com/paper/2212.09086/) (2022)
- [ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework](https://mlsanity.com/paper/2409.10289/) (2024)
- [Taming Continuous Posteriors for Latent Variational Dialogue Policies](https://mlsanity.com/paper/2205.07633/) (2022)
- [Partially Randomizing Transformer Weights for Dialogue Response Diversity](https://mlsanity.com/paper/2311.10943/) (2023)
- [Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings](https://mlsanity.com/paper/2204.02710/) (2022)
- [X-ReCoSa: Multi-Scale Context Aggregation For Multi-Turn Dialogue Generation](https://mlsanity.com/paper/2303.07833/) (2023)

## Abstract (arXiv)

Variational autoencoders (VAE) combined with hierarchical RNNs have emerged as a powerful framework for conversation modeling. However, they suffer from the notorious degeneration problem, where the decoders learn to ignore latent variables and reduce to vanilla RNNs. We empirically show that this degeneracy occurs mostly due to two reasons. First, the expressive power of hierarchical RNN decoders is often high enough to model the data using only its decoding distributions without relying on the latent variables. Second, the conditional VAE structure whose generation process is conditioned on a context, makes the range of training targets very sparse; that is, the RNN decoders can easily overfit to the training data ignoring the latent variables. To solve the degeneration problem, we propose a novel model named Variational Hierarchical Conversation RNNs (VHCR), involving two key ideas of (1) using a hierarchical structure of latent variables, and (2) exploiting an utterance drop regularization. With evaluations on two datasets of Cornell Movie Dialog and Ubuntu Dialog Corpus, we show that our VHCR successfully utilizes latent variables and outperforms state-of-the-art models for conversation generation. Moreover, it can perform several new utterance control tasks, thanks to its hierarchical latent structure.