# A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training

arXiv: https://arxiv.org/abs/2310.00597 · HTML: https://mlsanity.com/paper/2310.00597/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 1 Oct 2023.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://mlsanity.com/paper/2004.06871/) (2020)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Key-Value Retrieval Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1705.05414/) (2017)
- [UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2](https://mlsanity.com/paper/2012.03539/) (2020)
- [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)
- [ConveRT: Efficient and Accurate Conversational Representations from Transformers](https://mlsanity.com/paper/1911.03688/) (2019)
- [Few-shot Natural Language Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2002.12328/) (2020)
- [Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/1704.00057/) (2017)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://mlsanity.com/paper/2106.05555/) (2021)
- [Microsoft Dialogue Challenge: Building End-to-End Task-Completion Dialogue Systems](https://mlsanity.com/paper/1807.11125/) (2018)
- [Structured Fusion Networks for Dialog](https://mlsanity.com/paper/1907.10016/) (2019)
- [SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation](https://mlsanity.com/paper/2209.06664/) (2022)
- [SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding](https://mlsanity.com/paper/2209.06638/) (2022)
- [Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition](https://mlsanity.com/paper/2004.03809/) (2020)
- [Amendable Generation for Dialogue State Tracking](https://mlsanity.com/paper/2110.15659/) (2021)
- [OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue](https://mlsanity.com/paper/2209.04595/) (2022)

## Built on by (most cited first, 1 of 1)

- [MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations](https://mlsanity.com/paper/2512.13154/) (2025)

## Abstract (arXiv)

Pre-trained conversation models (PCMs) have achieved promising progress in recent years. However, existing PCMs for Task-oriented dialog (TOD) are insufficient for capturing the sequential nature of the TOD-related tasks, as well as for learning dialog policy information. To alleviate these problems, this paper proposes a task-progressive PCM with two policy-aware pre-training tasks. The model is pre-trained through three stages where TOD-related tasks are progressively employed according to the task logic of the TOD system. A global policy consistency task is designed to capture the multi-turn dialog policy sequential relation, and an act-based contrastive learning task is designed to capture similarities among samples with the same dialog policy. Our model achieves better results on both MultiWOZ and In-Car end-to-end dialog modeling benchmarks with only 18% parameters and 25% pre-training data compared to the previous state-of-the-art PCM, GALAXY.