# MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems

arXiv: https://arxiv.org/abs/2009.12005 · HTML: https://mlsanity.com/paper/2009.12005/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 30 of 103)

- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (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)
- [Guiding Large Language Models via Directional Stimulus Prompting](https://mlsanity.com/paper/2302.11520/) (2023)
- [Dialogue State Tracking with a Language Model using Schema-Driven Prompting](https://mlsanity.com/paper/2109.07506/) (2021)
- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation](https://mlsanity.com/paper/2109.05729/) (2021)
- [Few-Shot Bot: Prompt-Based Learning for Dialogue Systems](https://mlsanity.com/paper/2110.08118/) (2021)
- [Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking](https://mlsanity.com/paper/2105.04222/) (2021)
- [BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling](https://mlsanity.com/paper/2106.02787/) (2021)
- [Are LLMs All You Need for Task-Oriented Dialogue?](https://mlsanity.com/paper/2304.06556/) (2023)
- [Zero-Shot Dialogue State Tracking via Cross-Task Transfer](https://mlsanity.com/paper/2109.04655/) (2021)
- [Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://mlsanity.com/paper/2106.05555/) (2021)
- [In-Context Learning for Few-Shot Dialogue State Tracking](https://mlsanity.com/paper/2203.08568/) (2022)
- [Controllable Dialogue Simulation with In-Context Learning](https://mlsanity.com/paper/2210.04185/) (2022)
- [InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning](https://mlsanity.com/paper/2205.12673/) (2022)
- [SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting](https://mlsanity.com/paper/2305.09067/) (2023)
- [Transferable Dialogue Systems and User Simulators](https://mlsanity.com/paper/2107.11904/) (2021)
- [Large Language Models as Zero-shot Dialogue State Tracker through Function Calling](https://mlsanity.com/paper/2402.10466/) (2024)
- [GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2110.07679/) (2021)
- [Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System](https://mlsanity.com/paper/2305.02468/) (2023)
- [Slot Self-Attentive Dialogue State Tracking](https://mlsanity.com/paper/2101.09374/) (2021)
- [Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation](https://mlsanity.com/paper/2405.13037/) (2024)
- ["Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking](https://mlsanity.com/paper/2207.14627/) (2022)
- [Amendable Generation for Dialogue State Tracking](https://mlsanity.com/paper/2110.15659/) (2021)
- [Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking](https://mlsanity.com/paper/2203.01552/) (2022)
- [BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2205.02471/) (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)
- [Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2204.06677/) (2022)

## Abstract (arXiv)

In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems and alleviate the over-dependency on annotated data. MinTL is a simple yet effective transfer learning framework, which allows us to plug-and-play pre-trained seq2seq models, and jointly learn dialogue state tracking and dialogue response generation. Unlike previous approaches, which use a copy mechanism to "carryover" the old dialogue states to the new one, we introduce Levenshtein belief spans (Lev), that allows efficient dialogue state tracking with a minimal generation length. We instantiate our learning framework with two pre-trained backbones: T5 and BART, and evaluate them on MultiWOZ. Extensive experiments demonstrate that: 1) our systems establish new state-of-the-art results on end-to-end response generation, 2) MinTL-based systems are more robust than baseline methods in the low resource setting, and they achieve competitive results with only 20% training data, and 3) Lev greatly improves the inference efficiency.