# Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach

arXiv: https://arxiv.org/abs/1908.05854 · HTML: https://mlsanity.com/paper/1908.05854/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [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)
- [Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup](https://mlsanity.com/paper/2112.06204/) (2021)
- [A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting](https://mlsanity.com/paper/2104.02689/) (2021)
- [Dialog Flow Induction for Constrainable LLM-Based Chatbots](https://mlsanity.com/paper/2408.01623/) (2024)
- [Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems](https://mlsanity.com/paper/2307.07255/) (2023)
- [Reinforcement Learning for Few-Shot Text Generation Adaptation](https://mlsanity.com/paper/2111.11030/) (2021)

## Abstract (arXiv)

Learning with minimal data is one of the key challenges in the development of practical, production-ready goal-oriented dialogue systems. In a real-world enterprise setting where dialogue systems are developed rapidly and are expected to work robustly for an ever-growing variety of domains, products, and scenarios, efficient learning from a limited number of examples becomes indispensable. In this paper, we introduce a technique to achieve state-of-the-art dialogue generation performance in a few-shot setup, without using any annotated data. We do this by leveraging background knowledge from a larger, more highly represented dialogue source --- namely, the MetaLWOz dataset. We evaluate our model on the Stanford Multi-Domain Dialogue Dataset, consisting of human-human goal-oriented dialogues in in-car navigation, appointment scheduling, and weather information domains. We show that our few-shot approach achieves state-of-the art results on that dataset by consistently outperforming the previous best model in terms of BLEU and Entity F1 scores, while being more data-efficient by not requiring any data annotation.