# CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation

arXiv: https://arxiv.org/abs/2005.00329 · HTML: https://mlsanity.com/paper/2005.00329/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2020.

## Built on by (most cited first, 30 of 43)

- [TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition](https://mlsanity.com/paper/2305.03296/) (2023)
- [Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection](https://mlsanity.com/paper/2210.11715/) (2022)
- [Towards an Online Empathetic Chatbot with Emotion Causes](https://mlsanity.com/paper/2105.11903/) (2021)
- [LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification](https://mlsanity.com/paper/2106.01649/) (2021)
- [GTM: A Generative Triple-Wise Model for Conversational Question Generation](https://mlsanity.com/paper/2106.03635/) (2021)
- [Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness](https://mlsanity.com/paper/2210.03884/) (2022)
- [Probing Product Description Generation via Posterior Distillation](https://mlsanity.com/paper/2103.01594/) (2021)
- [Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization](https://mlsanity.com/paper/2109.06471/) (2021)
- [Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version](https://mlsanity.com/paper/2203.16110/) (2022)
- [Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation](https://mlsanity.com/paper/2102.09282/) (2021)
- [Modulating Language Models with Emotions](https://mlsanity.com/paper/2108.07886/) (2021)
- [Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge](https://mlsanity.com/paper/2109.03004/) (2021)
- [Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation](https://mlsanity.com/paper/2408.02976/) (2024)
- [Empathetic Dialog Generation with Fine-Grained Intents](https://mlsanity.com/paper/2105.06829/) (2021)
- [Knowledge-enhanced Memory Model for Emotional Support Conversation](https://mlsanity.com/paper/2310.07700/) (2023)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU](https://mlsanity.com/paper/2210.12499/) (2022)
- [A Critical Reflection and Forward Perspective on Empathy and Natural Language Processing](https://mlsanity.com/paper/2210.16604/) (2022)
- [In-sample Curriculum Learning by Sequence Completion for Natural Language Generation](https://mlsanity.com/paper/2211.11297/) (2022)
- [Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation](https://mlsanity.com/paper/2109.07779/) (2021)
- [Simulated Annealing for Emotional Dialogue Systems](https://mlsanity.com/paper/2109.10715/) (2021)
- [Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching](https://mlsanity.com/paper/2406.13361/) (2024)
- [A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking](https://mlsanity.com/paper/2210.15147/) (2022)
- [A Severity-Based Curriculum Learning Strategy for Arabic Medical Text Generation](https://mlsanity.com/paper/2604.06365/) (2026)
- [Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual Generator](https://mlsanity.com/paper/2105.08251/) (2021)
- [Towards Multi-Turn Empathetic Dialogs with Positive Emotion Elicitation](https://mlsanity.com/paper/2204.10509/) (2022)
- [A Unified Framework for Emotion Identification and Generation in Dialogues](https://mlsanity.com/paper/2205.15513/) (2022)
- [Modeling Content-Emotion Duality via Disentanglement for Empathetic Conversation](https://mlsanity.com/paper/2209.12495/) (2022)
- [ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy](https://mlsanity.com/paper/2308.06450/) (2023)
- [Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation](https://mlsanity.com/paper/2104.05224/) (2021)

## Abstract (arXiv)

Emotion-controllable response generation is an attractive and valuable task that aims to make open-domain conversations more empathetic and engaging. Existing methods mainly enhance the emotion expression by adding regularization terms to standard cross-entropy loss and thus influence the training process. However, due to the lack of further consideration of content consistency, the common problem of response generation tasks, safe response, is intensified. Besides, query emotions that can help model the relationship between query and response are simply ignored in previous models, which would further hurt the coherence. To alleviate these problems, we propose a novel framework named Curriculum Dual Learning (CDL) which extends the emotion-controllable response generation to a dual task to generate emotional responses and emotional queries alternatively. CDL utilizes two rewards focusing on emotion and content to improve the duality. Additionally, it applies curriculum learning to gradually generate high-quality responses based on the difficulties of expressing various emotions. Experimental results show that CDL significantly outperforms the baselines in terms of coherence, diversity, and relation to emotion factors.