An Emotion-controlled Dialog Response Generation Model with Dynamic Vocabulary
This work addresses the need for faster, human-like dialog systems in real-time applications, but it appears incremental as it combines existing techniques.
The authors tackled the problem of generating emotionally appropriate dialog responses efficiently for online systems by proposing an emotion-controlled model with a dynamic vocabulary mechanism, which improved speed as indicated by higher QPS.
In response generation task, proper sentimental expressions can obviously improve the human-like level of the responses. However, for real application in online systems, high QPS (queries per second, an indicator of the flow capacity of on-line systems) is required, and a dynamic vocabulary mechanism has been proved available in improving speed of generative models. In this paper, we proposed an emotion-controlled dialog response generation model based on the dynamic vocabulary mechanism, and the experimental results show the benefit of this model.