Emotion Conditioned Creative Dialog Generation
Not on the map. Why?
Abstract (arXiv)
We present a DialGPT based model for generating creative dialog responses that are conditioned based on one of the following emotions: anger, disgust, fear, happiness, pain, sadness and surprise. Our model is capable of producing a contextually apt response given an input sentence and a desired emotion label. Our model is capable of expressing the desired emotion with an accuracy of 0.6. The best performing emotions are neutral, fear and disgust. When measuring the strength of the expressed emotion, we find that anger, fear and disgust are expressed in the most strong fashion by the model.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 6 Dec 2022.
Builds on
10 of 29 references.
References · 10
- 2017Attention Is All You Needcited by 60,361
- 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
- 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
- 2021Datasets: A Community Library for Natural Language Processingcited by 530
- 2018Generating Informative and Diverse Conversational Responses via Adversarial Information Maximizationcited by 116
- 2020Fact-Enhanced Synthetic News Generationcited by 22
- 2021Empathetic Dialog Generation with Fine-Grained Intentscited by 7
- 2020Reasoning in Dialog: Improving Response Generation by Context Reading Comprehensioncited by 6
- 2021When a Computer Cracks a Joke: Automated Generation of Humorous Headlinescited by 2
- 2022Automatic Generation of Factual News Headlines in Finnishcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.