Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation

arXiv (Cornell University)

Abstract

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.

Authors 4

1. Lea Krause

   Vrije Universiteit Amsterdam

   Affiliation as printed

   Vrije Universiteit Amsterdam

2. Selene Báez Santamaría
3. Michiel van der Meer Aachen

   Leiden University

   Affiliation as printed

   Leiden University

4. Urja Khurana

   Vrije Universiteit Amsterdam

   Affiliation as printed

   Vrije Universiteit Amsterdam