Soft-Gated Self-Supervision Network for Action Reasoning: Soft-Gated Self-Supervision Network with Attention Mechanism and Joint Multi-Task Training Strategy 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.

[1]  David Vandyke,et al.  Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems , 2015, EMNLP.

[2]  Minlie Huang,et al.  Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog , 2019, EMNLP.

[3]  Yiming Yang,et al.  Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning , 2018, AAAI.

[4]  Baoyou Zheng,et al.  An Improved kNN Classifier for Epilepsy Diagnosis , 2020, IEEE Access.

[5]  Kam-Fai Wong,et al.  Integrating planning for task-completion dialogue policy learning , 2018, ACL.

[6]  Youwei Wang,et al.  Improved Adaboost Algorithm for Classification Based on Noise Confidence Degree and Weighted Feature Selection , 2020, IEEE Access.

[7]  Pascale Fung,et al.  Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems , 2018, ACL.

[8]  Bin Zou,et al.  Multiple Kernel SVM Based on Two-Stage Learning , 2020, IEEE Access.

[9]  Sungjin Lee,et al.  ConvLab: Multi-Domain End-to-End Dialog System Platform , 2019, ACL.

[10]  Chong Wang,et al.  Subgoal Discovery for Hierarchical Dialogue Policy Learning , 2018, EMNLP.

[11]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[12]  Stefan Ultes,et al.  Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management , 2017, SIGDIAL Conference.

[13]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[14]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[15]  David Vandyke,et al.  On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems , 2016, ACL.

[16]  Vladimir Vlasov,et al.  Few-Shot Generalization Across Dialogue Tasks , 2018, ArXiv.

[17]  David Vandyke,et al.  Multi-domain Neural Network Language Generation for Spoken Dialogue Systems , 2016, NAACL.