Task-Oriented Dialogue System as Natural Language Generation
This work addresses performance issues in task-oriented dialogue systems for applications like customer service, though it is incremental as it builds on existing pre-trained models.
The paper tackled the problem of dialogue entity inconsistency and catastrophic forgetting in task-oriented dialogue systems by proposing a GPT-Adapter-CopyNet network, which significantly outperformed baseline models on the DSTC8 Track 1 benchmark and MultiWOZ dataset.
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify complicated delexicalization prepossessing. However, directly applying this method heavily suffers from the dialogue entity inconsistency caused by the removal of delexicalized tokens, as well as the catastrophic forgetting problem of the pre-trained model during fine-tuning, leading to unsatisfactory performance. To alleviate these problems, we design a novel GPT-Adapter-CopyNet network, which incorporates the lightweight adapter and CopyNet modules into GPT-2 to achieve better performance on transfer learning and dialogue entity generation. Experimental results conducted on the DSTC8 Track 1 benchmark and MultiWOZ dataset demonstrate that our proposed approach significantly outperforms baseline models with a remarkable performance on automatic and human evaluations.