mlsanityData to 14 Oct 2026

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

arXiv 1605.06069 ↗First posted 19 May 2016cs.CL cs.AI cs.LGcited by 174

Not on the map. Why?

Abstract (arXiv)

Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue. In an effort to model this kind of generative process, we propose a neural network-based generative architecture, with latent stochastic variables that span a variable number of time steps. We apply the proposed model to the task of dialogue response generation and compare it with recent neural network architectures. We evaluate the model performance through automatic evaluation metrics and by carrying out a human evaluation. The experiments demonstrate that our model improves upon recently proposed models and that the latent variables facilitate the generation of long outputs and maintain the context.

Key facts. Cited by 174 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 1; 2021: 64; 2022: 56; 2023: 29; 2024: 9; 2025: 7; 2026: 6.

174 papers.

Sort:

By area:

  1. 2019Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialogcited by 284
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2020Human-centric Dialog Training via Offline Reinforcement Learningcited by 93
  4. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  5. 2021Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detectioncited by 56
  6. 2021Clockwork Variational Autoencoderscited by 42
  7. 2021Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speechcited by 42
  8. 2021One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profilescited by 39
  9. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 39
  10. 2021MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understandingcited by 36
  11. 2021CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversationcited by 35
  12. 2022DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generationcited by 35
38 more
  1. 2023Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Taskcited by 32
  2. 2021Semi-Supervised Variational Reasoning for Medical Dialogue Generationcited by 30
  3. 2021Commonsense-Focused Dialogues for Response Generation: An Empirical Studycited by 30
  4. 2022User-Centric Conversational Recommendation with Multi-Aspect User Modelingcited by 29
  5. 2021Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generationcited by 26
  6. 2021Semantic Representation for Dialogue Modelingcited by 24
  7. 2022C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender Systemcited by 24
  8. 2021Learning Neural Templates for Recommender Dialogue Systemcited by 22
  9. 2022Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Qualitycited by 22
  10. 2022Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendationcited by 22
  11. 2018Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learningcited by 21
  12. 2021Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interactioncited by 21
  13. 2022Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generationcited by 20
  14. 2023Learning Manifold Dimensions with Conditional Variational Autoencoderscited by 20
  15. 2021Maria: A Visual Experience Powered Conversational Agentcited by 19
  16. 2022Why is constrained neural language generation particularly challenging?cited by 19
  17. 2021Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoderscited by 18
  18. 2021A Review of Text Style Transfer using Deep Learningcited by 18
  19. 2022Data-to-text Generation with Variational Sequential Planningcited by 17
  20. 2022A Variational Hierarchical Model for Neural Cross-Lingual Summarizationcited by 17
  21. 2021GTM: A Generative Triple-Wise Model for Conversational Question Generationcited by 16
  22. 2021Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluationcited by 16
  23. 2021OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contextscited by 16
  24. 2022A Mixture-of-Expert Approach to RL-based Dialogue Managementcited by 16
  25. 2022Measuring and Improving Semantic Diversity of Dialogue Generationcited by 16
  26. 2021EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognitioncited by 15
  27. 2021Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbotscited by 15
  28. 2021Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classificationcited by 15
  29. 2021Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimizationcited by 15
  30. 2023History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue Systemcited by 15
  31. 2023TREA: Tree-Structure Reasoning Schema for Conversational Recommendationcited by 15
  32. 2021Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generationcited by 14
  33. 2021Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbotscited by 14
  34. 2021KECRS: Towards Knowledge-Enriched Conversational Recommendation Systemcited by 14
  35. 2021Unsupervised Enrichment of Persona-grounded Dialog with Background Storiescited by 14
  36. 2021DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformercited by 14
  37. 2021RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Modelscited by 14
  38. 2022Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agentscited by 14

50 most cited of 174 All 174 (JSON)