mlsanityData to 7 Oct 2026

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

arXiv 1703.10960 ↗First posted 31 Mar 2017cs.CL cs.AIcited by 222

Not on the map. Why?

Abstract (arXiv)

While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance. Finally, the training procedure is improved by introducing a bag-of-word loss. Our proposed models have been validated to generate significantly more diverse responses than baseline approaches and exhibit competence in discourse-level decision-making.

Key facts. Cited by 222 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 56; 2022: 74; 2023: 38; 2024: 32; 2025: 10; 2026: 11.

222 papers.

Sort:

By area:

  1. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 439
  2. 2022Long Time No See! Open-Domain Conversation with Long-Term Persona Memorycited by 107
  3. 2021A Comprehensive Assessment of Dialog Evaluation Metricscited by 90
  4. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 84
  5. 2021Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translationcited by 70
  6. 2020Dialogue Response Ranking Training with Large-Scale Human Feedback Datacited by 68
  7. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  8. 2021OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metricscited by 61
  9. 2021IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generationcited by 57
  10. 2023CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesiscited by 54
  11. 2022Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generationcited by 47
  12. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
38 more
  1. 2021Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speechcited by 42
  2. 2021Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generationcited by 35
  3. 2022DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generationcited by 35
  4. 2024MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Educationcited by 35
  5. 2021Multimodal Dialogue Response Generationcited by 32
  6. 2022Rethinking and Refining the Distinct Metriccited by 27
  7. 2021Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generationcited by 26
  8. 2021Diversifying Dialog Generation via Adaptive Label Smoothingcited by 25
  9. 2021LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generationcited by 24
  10. 2022GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimationcited by 24
  11. 2023Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Personacited by 24
  12. 2022Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Qualitycited by 22
  13. 2023An Overview on Language Models: Recent Developments and Outlookcited by 22
  14. 2022COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personascited by 20
  15. 2022Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generationcited by 20
  16. 2021Investigating Robustness of Dialog Models to Popular Figurative Language Constructscited by 19
  17. 2022A Personalized Dialogue Generator with Implicit User Persona Detectioncited by 19
  18. 2024Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluationscited by 19
  19. 2025Goal Alignment in LLM-Based User Simulators for Conversational AIcited by 19
  20. 2021Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoderscited by 18
  21. 2021Modeling Bilingual Conversational Characteristics for Neural Chat Translationcited by 18
  22. 2022Language modeling via stochastic processescited by 18
  23. 2022A Variational Hierarchical Model for Neural Cross-Lingual Summarizationcited by 17
  24. 2022Improving Personality Consistency in Conversation by Persona Extendingcited by 17
  25. 2023Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialoguescited by 17
  26. 2021Learning to Select External Knowledge with Multi-Scale Negative Samplingcited by 16
  27. 2021Assessing Dialogue Systems with Distribution Distancescited by 16
  28. 2021GTM: A Generative Triple-Wise Model for Conversational Question Generationcited by 16
  29. 2021OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contextscited by 16
  30. 2022A Corpus for Understanding and Generating Moral Storiescited by 16
  31. 2022Measuring and Improving Semantic Diversity of Dialogue Generationcited by 16
  32. 2021Automatically Select Emotion for Response via Personality-affected Emotion Transitioncited by 15
  33. 2021Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimizationcited by 15
  34. 2024SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinementcited by 15
  35. 2021KECRS: Towards Knowledge-Enriched Conversational Recommendation Systemcited by 14
  36. 2021Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classificationcited by 14
  37. 2021DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformercited by 14
  38. 2022Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agentscited by 14

50 most cited of 222 All 222 (JSON)