Soft-Gated Self-Supervision Network for Action Reasoning

Behavior decision-making in the dialogue domain is the key to the success of the dialogue system. Existing machine learning algorithm based on statistics and an deep learning algorithm based on pre-training are difficult to adapt to all tasks. Therefore, this paper proposes a multi-task classification model based on soft gating. Firstly, based on the existing models, a multi-task model suitable for specific fields is designed, which makes the model fully consider the characteristics of the data set itself. Secondly, soft gating is used to divide the model to reduce the interaction between model parameters. Then, we manually annotate and extend the existing session behavior data set. Finally, the trained model is used to recognize dialogue behavior. The experimental results show that the accuracy of the score is 89.1%. The experimental results show that the performance of SGSAM better than other models.