Conversation Style Transfer using Few-Shot Learning

TL;DR

This paper introduces a few-shot learning method for conversation style transfer that leverages multi-turn context to improve style matching and semantic appropriateness in dialogue systems.

Contribution

It presents a novel in-context learning approach for conversation style transfer using style-free dialogues as pivots, addressing contextual and definitional challenges.

Findings

Multi-turn context improves style transfer accuracy.

The approach enhances semantic correctness and appropriateness.

Style transfer benefits downstream intent classification tasks.

Abstract

Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e.g., formality). When applying style transfer in conversations such as task-oriented dialogues, existing approaches suffer from these limitations as context can play an important role and the style attributes are often difficult to define in conversations. In this paper, we introduce conversation style transfer as a few-shot learning problem, where the model learns to perform style transfer by observing only a few example dialogues in the target style. We propose a novel in-context learning approach to solve the task with style-free dialogues as a pivot. Human evaluation shows that by incorporating multi-turn context, the model is able to match the target style while having better appropriateness and semantic correctness compared to utterance/sentence-level style transfer. Additionally, we show that conversation style transfer can also benefit downstream tasks. For example, in multi-domain intent classification tasks, the F1 scores improve after transferring the style of training data to match the style of the test data.