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

arXiv: https://arxiv.org/abs/1909.05528 · HTML: https://mlsanity.com/paper/1909.05528/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.00783/) (2021)
- [Semi-Supervised Variational Reasoning for Medical Dialogue Generation](https://mlsanity.com/paper/2105.06071/) (2021)
- [DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues](https://mlsanity.com/paper/2106.00920/) (2021)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering](https://mlsanity.com/paper/2104.10283/) (2021)
- [3D Question Answering for City Scene Understanding](https://mlsanity.com/paper/2407.17398/) (2024)
- [HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations](https://mlsanity.com/paper/2106.00162/) (2021)
- [Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems](https://mlsanity.com/paper/2204.00763/) (2022)
- [Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory](https://mlsanity.com/paper/2106.02317/) (2021)
- [Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues](https://mlsanity.com/paper/2305.13690/) (2023)
- [HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management](https://mlsanity.com/paper/2105.06041/) (2021)
- [Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning](https://mlsanity.com/paper/2207.12185/) (2022)
- [OmniDialog: An Omnipotent Pre-training Model for Task-Oriented Dialogue System](https://mlsanity.com/paper/2312.16864/) (2023)
- [End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management](https://mlsanity.com/paper/2106.11796/) (2021)
- [Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition](https://mlsanity.com/paper/2505.15922/) (2025)
- [SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation](https://mlsanity.com/paper/2307.04907/) (2023)
- [Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback](https://mlsanity.com/paper/2403.11330/) (2024)
- [ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling](https://mlsanity.com/paper/2603.09691/) (2026)
- [SoK: Semantic Decision Engines in Network Control Loops](https://mlsanity.com/paper/2610.06425/) (2026)

## Abstract (arXiv)

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.