# Structured Fusion Networks for Dialog

arXiv: https://arxiv.org/abs/1907.10016 · HTML: https://mlsanity.com/paper/1907.10016/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

## Built on by (most cited first, 30 of 40)

- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [GODEL: Large-Scale Pre-Training for Goal-Directed Dialog](https://mlsanity.com/paper/2206.11309/) (2022)
- [Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://mlsanity.com/paper/2106.05555/) (2021)
- [Transferable Dialogue Systems and User Simulators](https://mlsanity.com/paper/2107.11904/) (2021)
- [SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation](https://mlsanity.com/paper/2209.06664/) (2022)
- [Semi-Supervised Variational Reasoning for Medical Dialogue Generation](https://mlsanity.com/paper/2105.06071/) (2021)
- [Pretraining the Noisy Channel Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2103.10518/) (2021)
- [ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format](https://mlsanity.com/paper/2211.17148/) (2022)
- [Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems](https://mlsanity.com/paper/2302.10342/) (2023)
- [PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts](https://mlsanity.com/paper/2305.14839/) (2023)
- [Domain State Tracking for a Simplified Dialogue System](https://mlsanity.com/paper/2103.06648/) (2021)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [Task-Oriented Dialogue System as Natural Language Generation](https://mlsanity.com/paper/2108.13679/) (2021)
- [Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems](https://mlsanity.com/paper/2109.04314/) (2021)
- [TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons](https://mlsanity.com/paper/2504.19982/) (2025)
- [CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation](https://mlsanity.com/paper/2211.11617/) (2022)
- [Response-act Guided Reinforced Dialogue Generation for Mental Health Counseling](https://mlsanity.com/paper/2301.12729/) (2023)
- [Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory](https://mlsanity.com/paper/2106.02317/) (2021)
- [Autoregressive Entity Generation for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2209.08708/) (2022)
- [HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management](https://mlsanity.com/paper/2105.06041/) (2021)
- [OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience](https://mlsanity.com/paper/2206.12449/) (2022)
- [Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning](https://mlsanity.com/paper/2207.12185/) (2022)
- [InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2310.08885/) (2023)
- [Causal-aware Safe Policy Improvement for Task-oriented dialogue](https://mlsanity.com/paper/2103.06370/) (2021)
- [A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining](https://mlsanity.com/paper/2102.04506/) (2021)
- [End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management](https://mlsanity.com/paper/2106.11796/) (2021)
- [Advancing Semi-Supervised Task Oriented Dialog Systems by JSA Learning of Discrete Latent Variable Models](https://mlsanity.com/paper/2207.12235/) (2022)
- [Dialogue Evaluation with Offline Reinforcement Learning](https://mlsanity.com/paper/2209.00876/) (2022)
- [Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?](https://mlsanity.com/paper/2210.12942/) (2022)

## Abstract (arXiv)

Neural dialog models have exhibited strong performance, however their end-to-end nature lacks a representation of the explicit structure of dialog. This results in a loss of generalizability, controllability and a data-hungry nature. Conversely, more traditional dialog systems do have strong models of explicit structure. This paper introduces several approaches for explicitly incorporating structure into neural models of dialog. Structured Fusion Networks first learn neural dialog modules corresponding to the structured components of traditional dialog systems and then incorporate these modules in a higher-level generative model. Structured Fusion Networks obtain strong results on the MultiWOZ dataset, both with and without reinforcement learning. Structured Fusion Networks are shown to have several valuable properties, including better domain generalizability, improved performance in reduced data scenarios and robustness to divergence during reinforcement learning.