# An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

arXiv: https://arxiv.org/abs/2209.14627 · HTML: https://mlsanity.com/paper/2209.14627/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 61 references that are in the map.
- First posted on arXiv 29 Sep 2022.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning](https://mlsanity.com/paper/1705.07761/) (2017)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [Expectation-Maximization Attention Networks for Semantic Segmentation](https://mlsanity.com/paper/1907.13426/) (2019)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space](https://mlsanity.com/paper/2004.04092/) (2020)
- [Adversarial Learning for Neural Dialogue Generation](https://mlsanity.com/paper/1701.06547/) (2017)
- [RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems](https://mlsanity.com/paper/1701.03079/) (2017)
- [Mixture Models for Diverse Machine Translation: Tricks of the Trade](https://mlsanity.com/paper/1902.07816/) (2019)
- [Learning an Unreferenced Metric for Online Dialogue Evaluation](https://mlsanity.com/paper/2005.00583/) (2020)
- [DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder](https://mlsanity.com/paper/1805.12352/) (2018)
- [DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances](https://mlsanity.com/paper/2012.01775/) (2020)

## Built on by (most cited first, 11 of 11)

- [f-Divergence Minimization for Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/2307.15190/) (2023)
- [Teacher Forcing Recovers Reward Functions for Text Generation](https://mlsanity.com/paper/2210.08708/) (2022)
- [DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questions](https://mlsanity.com/paper/2406.19356/) (2024)
- [Ensemble Distillation for Unsupervised Constituency Parsing](https://mlsanity.com/paper/2310.01717/) (2023)
- [MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation](https://mlsanity.com/paper/2305.12733/) (2023)
- [LLMR: Knowledge Distillation with a Large Language Model-Induced Reward](https://mlsanity.com/paper/2409.12500/) (2024)
- [Multi-modal Data based Semi-Supervised Learning for Vehicle Positioning](https://mlsanity.com/paper/2410.20680/) (2024)
- [Multiple Choice Learning of Low-Rank Adapters for Language Modeling](https://mlsanity.com/paper/2507.10419/) (2025)
- [EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation](https://mlsanity.com/paper/2403.00144/) (2024)
- [PMODE: Theoretically Grounded and Modular Mixture Modeling](https://mlsanity.com/paper/2508.21396/) (2025)
- [Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement](https://mlsanity.com/paper/2605.23190/) (2026)

## Abstract (arXiv)

Open-domain dialogue systems aim to interact with humans through natural language texts in an open-ended fashion. Despite the recent success of super large dialogue systems such as ChatGPT, using medium-to-small-sized dialogue systems remains the common practice as they are more lightweight and accessible; however, generating diverse dialogue responses is challenging, especially with smaller models. In this work, we propose an Equal-size Hard Expectation--Maximization (EqHard-EM) algorithm to train a multi-decoder model for diverse dialogue generation. Our algorithm assigns a sample to a decoder in a hard manner and additionally imposes an equal-assignment constraint to ensure that all decoders are well-trained. We provide detailed theoretical analysis to justify our approach. Further, experiments on two large-scale open-domain dialogue datasets verify that our EqHard-EM algorithm generates high-quality diverse responses.