mlsanityData to 14 Oct 2026

Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders

arXiv 2106.03410 ↗First posted 7 Jun 2021cs.CLcited by 18

Not on the map. Why?

Abstract (arXiv)

Conditional Variational AutoEncoder (CVAE) effectively increases the diversity and informativeness of responses in open-ended dialogue generation tasks through enriching the context vector with sampled latent variables. However, due to the inherent one-to-many and many-to-one phenomena in human dialogues, the sampled latent variables may not correctly reflect the contexts' semantics, leading to irrelevant and incoherent generated responses. To resolve this problem, we propose Self-separated Conditional Variational AutoEncoder (abbreviated as SepaCVAE) that introduces group information to regularize the latent variables, which enhances CVAE by improving the responses' relevance and coherence while maintaining their diversity and informativeness. SepaCVAE actively divides the input data into groups, and then widens the absolute difference between data pairs from distinct groups, while narrowing the relative distance between data pairs in the same group. Empirical results from automatic evaluation and detailed analysis demonstrate that SepaCVAE can significantly boost responses in well-established open-domain dialogue datasets.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

37 of 53 references.

References · 37

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  6. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  7. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  8. 2015Generating Sentences from a Continuous Spacecited by 612
  9. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 376
  10. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  11. 2016Deep Reinforcement Learning for Dialogue Generationcited by 288
  12. 2016A Persona-Based Neural Conversation Modelcited by 223
25 more
  1. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  2. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  3. 2020Representation Learning via Invariant Causal Mechanismscited by 199
  4. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  5. 2017A Knowledge-Grounded Neural Conversation Modelcited by 136
  6. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  7. 2018Generating Informative and Diverse Conversational Responses via Adversarial Information Maximizationcited by 116
  8. 2017Adversarial Learning for Neural Dialogue Generationcited by 103
  9. 2015A Neural Network Approach to Context-Sensitive Generation of Conversational Responsescited by 98
  10. 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
  11. 2020You Impress Me: Dialogue Generation via Mutual Persona Perceptioncited by 85
  12. 2015A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestioncited by 68
  13. 2018DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encodercited by 44
  14. 2018DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Textcited by 40
  15. 2018Generating More Interesting Responses in Neural Conversation Models with Distributional Constraintscited by 33
  16. 2019Improving Neural Conversational Models with Entropy-Based Data Filteringcited by 30
  17. 2018Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversitycited by 27
  18. 2017Neural Machine Translation and Sequence-to-sequence Models: A Tutorialcited by 25
  19. 2019Jointly Optimizing Diversity and Relevance in Neural Response Generationcited by 22
  20. 2017A Conditional Variational Framework for Dialog Generationcited by 16
  21. 2019Self-Supervised Dialogue Learningcited by 16
  22. 2020Regularizing Dialogue Generation by Imitating Implicit Scenarioscited by 16
  23. 2020Group-wise Contrastive Learning for Neural Dialogue Generationcited by 15
  24. 2017Steering Output Style and Topic in Neural Response Generationcited by 10
  25. 2020Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Networkcited by 9

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 7; 2023: 6; 2024: 3; 2025: 1.

18 papers.

Sort:

By area:

  1. 2023Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Personacited by 24
  2. 2024Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluationscited by 20
  3. 2022Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priorscited by 13
  4. 2023Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologuecited by 11
  5. 2022An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasetscited by 8
  6. 2022PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanismcited by 6
  7. 2024DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Spacecited by 6
  8. 2022Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variablescited by 5
  9. 2023An Empirical Bayes Framework for Open-Domain Dialogue Generationcited by 5
  10. 2022Hierarchical Inductive Transfer for Continual Dialogue Learningcited by 3
  11. 2025Modeling the One-to-Many Property in Open-Domain Dialogue with LLMscited by 3
  12. 2021A Speaker-aware Parallel Hierarchical Attentive Encoder-Decoder Model for Multi-turn Dialogue Generationcited by 2
6 more
  1. 2022Stop Filtering: Multi-View Attribute-Enhanced Dialogue Learningcited by 2
  2. 2024Rumor Detection on Social Media with Reinforcement Learning-based Key Propagation Graph Generatorcited by 2
  3. 2022Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encodercited by 1
  4. 2023Heterogeneous-Branch Collaborative Learning for Dialogue Generationcited by 1
  5. 2023Partially Randomizing Transformer Weights for Dialogue Response Diversitycited by 1
  6. 2023Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generationcited by 0