Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation
This work addresses response generation for conversational AI systems, but it appears incremental as it builds on existing few-shot and prompting methods without major breakthroughs.
The paper tackled response generation in task-oriented conversational modeling by augmenting data with few-shot learning and using waterfall prompting with GPT-3 and ChatGPT, resulting in three approaches for DSTC11, though no concrete performance numbers were provided.
This paper discusses our approaches for task-oriented conversational modelling using subjective knowledge, with a particular emphasis on response generation. Our methodology was shaped by an extensive data analysis that evaluated key factors such as response length, sentiment, and dialogue acts present in the provided dataset. We used few-shot learning to augment the data with newly generated subjective knowledge items and present three approaches for DSTC11: (1) task-specific model exploration, (2) incorporation of the most frequent question into all generated responses, and (3) a waterfall prompting technique using a combination of both GPT-3 and ChatGPT.