MOSS: End-to-End Dialog System Framework with Modular Supervision

TL;DR

MOSS is a flexible end-to-end dialog system framework that uses modular supervision from multiple dialog modules to improve performance with limited training data, especially on complex tasks.

Contribution

The paper introduces MOSS, a novel encoder-decoder framework that incorporates supervision from various dialog modules, enhancing data efficiency and adaptability in dialog systems.

Findings

MOSS outperforms state-of-the-art models with only 60% of training data on CamRest676.

MOSS achieves better results with 40% data on a new complex Chinese troubleshooting dataset.

Modular supervision significantly benefits complex dialog tasks with large state and action spaces.

Abstract

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.