mlsanityData to 14 Oct 2026

Transferable Persona-Grounded Dialogues via Grounded Minimal Edits

arXiv 2109.07713 ↗First posted 16 Sep 2021cs.CL cs.AI cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Grounded dialogue models generate responses that are grounded on certain concepts. Limited by the distribution of grounded dialogue data, models trained on such data face the transferability challenges in terms of the data distribution and the type of grounded concepts. To address the challenges, we propose the grounded minimal editing framework, which minimally edits existing responses to be grounded on the given concept. Focusing on personas, we propose Grounded Minimal Editor (GME), which learns to edit by disentangling and recombining persona-related and persona-agnostic parts of the response. To evaluate persona-grounded minimal editing, we present the PersonaMinEdit dataset, and experimental results show that GME outperforms competitive baselines by a large margin. To evaluate the transferability, we experiment on the test set of BlendedSkillTalk and show that GME can edit dialogue models' responses to largely improve their persona consistency while preserving the use of knowledge and empathy.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 41 of its 59 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

41 of 59 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  4. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  5. 2020Recipes for building an open-domain chatbotcited by 593
  6. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  7. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
  8. 2016A Persona-Based Neural Conversation Modelcited by 223
  9. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 211
  10. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  11. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  12. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
29 more
  1. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  2. 2017ParlAI: A Dialog Research Software Platformcited by 139
  3. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  4. 2018Dialogue Natural Language Inferencecited by 135
  5. 2020Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skillscited by 131
  6. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 106
  7. 2019Counterfactual Story Reasoning and Generationcited by 88
  8. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  9. 2019Personalizing Dialogue Agents via Meta-Learningcited by 83
  10. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  11. 2019Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfercited by 81
  12. 2018Image Chat: Engaging Grounded Conversationscited by 77
  13. 2020Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Textcited by 75
  14. 2021Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approachcited by 75
  15. 2020A Probabilistic Formulation of Unsupervised Text Style Transfercited by 70
  16. 2020I like fish, especially dolphins: Addressing Contradictions in Dialogue Modelingcited by 68
  17. 2019A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfercited by 65
  18. 2020Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoningcited by 65
  19. 2019Generating Sentences from Disentangled Syntactic and Semantic Spacescited by 59
  20. 2019Exploiting Persona Information for Diverse Generation of Conversational Responsescited by 58
  21. 2020Towards Persona-Based Empathetic Conversational Modelscited by 53
  22. 2018Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memorycited by 49
  23. 2019"Mask and Infill" : Applying Masked Language Model to Sentiment Transfercited by 48
  24. 2020Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generationcited by 41
  25. 2018Response Generation by Context-aware Prototype Editingcited by 40
  26. 2019Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbotscited by 23
  27. 2017Neural Personalized Response Generation as Domain Adaptationcited by 19
  28. 2020Contextual Text Style Transfercited by 17
  29. 2020Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfercited by 15

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 2; 2024: 2; 2025: 1.

10 papers.

  1. 2022Rethinking and Refining the Distinct Metriccited by 27
  2. 2024Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluationscited by 20
  3. 2022Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in Chinacited by 17
  4. 2023Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularizationcited by 17
  5. 2022A Critical Reflection and Forward Perspective on Empathy and Natural Language Processingcited by 4
  6. 2022Replacing Language Model for Style Transfercited by 3
  7. 2023Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialoguecited by 1
  8. 2025Persona-Aware Alignment Framework for Personalized Dialogue Generationcited by 1
  9. 2022Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)cited by 0
  10. 2024Granular Change Accuracy: A More Accurate Performance Metric for Dialogue State Trackingcited by 0