mlsanityData to 7 Oct 2026

An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

arXiv 2209.14627 ↗First posted 29 Sep 2022cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 40 of its 61 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

40 of 61 references.

References · 40

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2017Proximal Policy Optimization Algorithmscited by 14,441
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  10. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  11. 2015Generating Sentences from a Continuous Spacecited by 607
  12. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 575
28 more
  1. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  2. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 318
  3. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
  4. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  5. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  6. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  7. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  8. 2015A Neural Conversational Modelcited by 195
  9. 2018The Design and Implementation of XiaoIce, an Empathetic Social Chatbotcited by 172
  10. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147
  11. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  12. 2020Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Spacecited by 114
  13. 2017Adversarial Learning for Neural Dialogue Generationcited by 103
  14. 2017RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systemscited by 88
  15. 2019Mixture Models for Diverse Machine Translation: Tricks of the Tradecited by 77
  16. 2020Learning an Unreferenced Metric for Online Dialogue Evaluationcited by 52
  17. 2018DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encodercited by 44
  18. 2020DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterancescited by 36
  19. 2016Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversationcited by 35
  20. 2022DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generationcited by 35
  21. 2017Variational Attention for Sequence-to-Sequence Modelscited by 29
  22. 2021Diversifying Dialog Generation via Adaptive Label Smoothingcited by 25
  23. 2021Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systemscited by 17
  24. 2018Generating Multiple Diverse Responses for Short-Text Conversationcited by 13
  25. 2017Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translationcited by 12
  26. 2020Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Networkcited by 9
  27. 2022An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasetscited by 8
  28. 2021Generalized Equivariance and Preferential Labeling for GNN Node Classificationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 4; 2025: 2; 2026: 1.

11 papers.

  1. 2023f-Divergence Minimization for Sequence-Level Knowledge Distillationcited by 112
  2. 2022Teacher Forcing Recovers Reward Functions for Text Generationcited by 11
  3. 2024DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice Questionscited by 7
  4. 2023Ensemble Distillation for Unsupervised Constituency Parsingcited by 6
  5. 2023MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generationcited by 5
  6. 2024LLMR: Knowledge Distillation with a Large Language Model-Induced Rewardcited by 3
  7. 2024Multi-modal Data based Semi-Supervised Learning for Vehicle Positioningcited by 2
  8. 2025Multiple Choice Learning of Low-Rank Adapters for Language Modelingcited by 2
  9. 2024EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translationcited by 1
  10. 2025PMODE: Theoretically Grounded and Modular Mixture Modelingcited by 1
  11. 2026Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancementcited by 0