mlsanityData to 7 Oct 2026

Affect-Driven Dialog Generation

arXiv 1904.02793 ↗First posted 4 Apr 2019cs.CL cs.AI cs.LGcited by 50

Not on the map. Why?

Abstract (arXiv)

The majority of current systems for end-to-end dialog generation focus on response quality without an explicit control over the affective content of the responses. In this paper, we present an affect-driven dialog system, which generates emotional responses in a controlled manner using a continuous representation of emotions. The system achieves this by modeling emotions at a word and sequence level using: (1) a vector representation of the desired emotion, (2) an affect regularizer, which penalizes neutral words, and (3) an affect sampling method, which forces the neural network to generate diverse words that are emotionally relevant. During inference, we use a reranking procedure that aims to extract the most emotionally relevant responses using a human-in-the-loop optimization process. We study the performance of our system in terms of both quantitative (BLEU score and response diversity), and qualitative (emotional appropriateness) measures.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 14; 2023: 10; 2024: 7; 2025: 2; 2026: 1.

50 papers.

Sort:

By area:

  1. 2022Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generationcited by 73
  2. 2021Automatic Text Evaluation through the Lens of Wasserstein Barycenterscited by 38
  3. 2021A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representationscited by 37
  4. 2024Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thoughtcited by 34
  5. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  6. 2022COGMEN: COntextualized GNN based Multimodal Emotion recognitioNcited by 29
  7. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  8. 2021A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regionscited by 17
  9. 2021An End-to-End Network for Emotion-Cause Pair Extractioncited by 15
  10. 2021Automatically Select Emotion for Response via Personality-affected Emotion Transitioncited by 15
  11. 2021Improving Multimodal fusion via Mutual Dependency Maximisationcited by 15
  12. 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
38 more
  1. 2022Learning Disentangled Textual Representations via Statistical Measures of Similaritycited by 14
  2. 2023Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarkscited by 14
  3. 2021Beam Search with Bidirectional Strategies for Neural Response Generationcited by 12
  4. 2021Code-switched inspired losses for generic spoken dialog representationscited by 10
  5. 2022The Glass Ceiling of Automatic Evaluation in Natural Language Generationcited by 10
  6. 2021Fine-Grained Emotion Prediction by Modeling Emotion Definitionscited by 9
  7. 2021Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shiftscited by 9
  8. 2023EmoUS: Simulating User Emotions in Task-Oriented Dialoguescited by 9
  9. 2021Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledgecited by 8
  10. 2024Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generationcited by 8
  11. 2024MOPO: Multi-Objective Prompt Optimization for Affective Text Generationcited by 8
  12. 2021Empathetic Dialog Generation with Fine-Grained Intentscited by 7
  13. 2024A Review of Human Emotion Synthesis Based on Generative Technologycited by 7
  14. 2023Affective Natural Language Generation of Event Descriptions through Fine-grained Appraisal Conditionscited by 4
  15. 2023The Importance of Multimodal Emotion Conditioning and Affect Consistency for Embodied Conversational Agentscited by 4
  16. 2023Transductive Learning for Textual Few-Shot Classification in API-based Embedding Modelscited by 4
  17. 2021Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generationcited by 3
  18. 2022Multi-Task Learning Framework for Extracting Emotion Cause Span and Entailment in Conversationscited by 3
  19. 2022Beyond Mahalanobis-Based Scores for Textual OOD Detectioncited by 3
  20. 2023Toward Stronger Textual Attack Detectorscited by 3
  21. 2024Personality-affected Emotion Generation in Dialog Systemscited by 3
  22. 2022CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspectivecited by 2
  23. 2025LLM-based Affective Text Generation Quality Based on Different Quantization Valuescited by 2
  24. 2021Humor@IITK at SemEval-2021 Task 7: Large Language Models for Quantifying Humor and Offensivenesscited by 1
  25. 2021Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual Generatorcited by 1
  26. 2022Towards Multi-Turn Empathetic Dialogs with Positive Emotion Elicitationcited by 1
  27. 2022A Unified Framework for Emotion Identification and Generation in Dialoguescited by 1
  28. 2022Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systemscited by 1
  29. 2022Modeling Content-Emotion Duality via Disentanglement for Empathetic Conversationcited by 1
  30. 2023Dynamic Causal Disentanglement Model for Dialogue Emotion Detectioncited by 1
  31. 2023A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classificationcited by 1
  32. 2025Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communicationcited by 1
  33. 2022What are the best systems? New perspectives on NLP Benchmarkingcited by 0
  34. 2022Empathetic Response Generation with State Managementcited by 0
  35. 2023Predicting Evoked Emotions in Conversationscited by 0
  36. 2024IITK at SemEval-2024 Task 10: Who is the speaker? Improving Emotion Recognition and Flip Reasoning in Conversations via Speaker Embeddingscited by 0
  37. 2024Closing the Affective Loop via Experience-Driven Reinforcement Learning Designerscited by 0
  38. 2026Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Textscited by 0