An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
This work addresses the need for more nuanced and controllable dialogue generation in AI systems, though it is incremental as it builds on existing adversarial and sequence-to-sequence methods.
The authors tackled the problem of generating dialogue responses with explicit sentiment control, achieving results that were both semantically reasonable and sentiment-controlled as validated by automatic and human evaluations.
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.