MOSS: End-to-End Dialog System Framework with Modular Supervision
This addresses data efficiency for dialog systems, offering a flexible solution for real-world deployment, though it is incremental in leveraging existing modular supervision.
The paper tackles the problem of limited training data for end-to-end task-oriented dialog systems by proposing MOSS, a framework that incorporates supervision from intermediate dialog modules, achieving state-of-the-art performance with only 60% of data on CamRest676 and 40% on a complex dataset.
A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning, and natural language generation. With only 60% of the training data, MOSS-all (i.e., MOSS with supervision from all four dialog modules) outperforms state-of-the-art models on CamRest676. Moreover, introducing modular supervision has even bigger benefits when the dialog task has a more complex dialog state and action space. With only 40% of the training data, MOSS-all outperforms the state-of-the-art model on a complex laptop network troubleshooting dataset, LaptopNetwork, that we introduced. LaptopNetwork consists of conversations between real customers and customer service agents in Chinese. Moreover, MOSS framework can accommodate dialogs that have supervision from different dialog modules at both the framework level and model level. Therefore, MOSS is extremely flexible to update in a real-world deployment.