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

## TL;DR

This paper presents a transfer learning method for goal-oriented dialogue generation that achieves state-of-the-art results in few-shot settings without annotated data, by leveraging background knowledge from a larger dialogue dataset.

## Contribution

Introduces a novel transfer learning approach that enables high-quality dialogue generation in few-shot scenarios without the need for annotated data.

## Key findings

- Outperforms previous models on BLEU and Entity F1 scores
- Achieves state-of-the-art results in few-shot dialogue generation
- Does not require annotated data for training

## Abstract

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.