# Teacher-Student Framework Enhanced Multi-domain Dialogue Generation

arXiv: https://arxiv.org/abs/1908.07137 · HTML: https://mlsanity.com/paper/1908.07137/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2019.

## Built on by (most cited first, 8 of 8)

- [Transferable Dialogue Systems and User Simulators](https://mlsanity.com/paper/2107.11904/) (2021)
- [Pretraining the Noisy Channel Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2103.10518/) (2021)
- [Task-Oriented Dialogue System as Natural Language Generation](https://mlsanity.com/paper/2108.13679/) (2021)
- [A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting](https://mlsanity.com/paper/2104.02689/) (2021)
- [OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue](https://mlsanity.com/paper/2209.04595/) (2022)
- [ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognition](https://mlsanity.com/paper/2301.08855/) (2023)
- [A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation](https://mlsanity.com/paper/2406.09881/) (2024)
- [MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2306.07994/) (2023)

## Abstract (arXiv)

Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-defined features as dialogue states and apply a state tracker to extract these features. However, the performance of such a system is limited by the error propagation of a state tracker. In this paper, we propose a dialogue generation model that needs no external state trackers and still benefits from human-labeled semantic data. By using a teacher-student framework, several teacher models are firstly trained in their individual domains, learn dialogue policies from labeled states. And then the learned knowledge and experience are merged and transferred to a universal student model, which takes raw utterance as its input. Experiments show that the dialogue system trained under our framework outperforms the one uses a belief tracker.