Generating Responses Expressing Emotion in an Open-domain Dialogue System
This work addresses the issue of emotional blandness in conversational AI for users seeking more engaging interactions, representing an incremental improvement over existing methods.
The paper tackled the problem of generating emotionally expressive responses in open-domain dialogue systems, where neural models often produce dull and generic outputs. The proposed encoder-decoder model with multiple attention layers achieved the best overall performance in expressing required emotions, showing promising results in most cases.
Neural network-based Open-ended conversational agents automatically generate responses based on predictive models learned from a large number of pairs of utterances. The generated responses are typically acceptable as a sentence but are often dull, generic, and certainly devoid of any emotion. In this paper, we present neural models that learn to express a given emotion in the generated response. We propose four models and evaluate them against 3 baselines. An encoder-decoder framework-based model with multiple attention layers provides the best overall performance in terms of expressing the required emotion. While it does not outperform other models on all emotions, it presents promising results in most cases.