# An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation

arXiv: https://arxiv.org/abs/1901.07129 · HTML: https://mlsanity.com/paper/1901.07129/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2019.

## Built on by (most cited first, 5 of 5)

- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Modulating Language Models with Emotions](https://mlsanity.com/paper/2108.07886/) (2021)
- [A Review of Human Emotion Synthesis Based on Generative Technology](https://mlsanity.com/paper/2412.07116/) (2024)
- [Text Style Transfer: An Introductory Overview](https://mlsanity.com/paper/2407.14822/) (2024)
- [Predicting Evoked Emotions in Conversations](https://mlsanity.com/paper/2401.00383/) (2023)

## Abstract (arXiv)

In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via sentiment labels. Our proposed model is based on the paradigm of conditional adversarial learning; the training of a sentiment-controlled dialogue generator is assisted by an adversarial discriminator which assesses the fluency and feasibility of the response generating from the dialogue history and a given sentiment label. Because of the flexibility of our framework, the generator could be a standard sequence-to-sequence (SEQ2SEQ) model or a more complicated one such as a conditional variational autoencoder-based SEQ2SEQ model. Experimental results using automatic and human evaluation both demonstrate that our proposed framework is able to generate both semantically reasonable and sentiment-controlled dialogue responses.