Conversation Style Transfer using Few-Shot Learning
This addresses the problem of context-aware style transfer in conversations for dialogue systems, though it is incremental by building on few-shot learning methods.
The paper tackles conversation style transfer by framing it as a few-shot learning problem, using an in-context learning approach with style-free dialogues as a pivot. Human evaluation shows the model matches target styles better in appropriateness and semantic correctness than sentence-level methods, and it improves F1 scores in multi-domain intent classification tasks.
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.