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

Lea Krause, Selene Báez Santamaría, Michiel van der Meer, Urja Khurana


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.
Anthology ID:
2023.dstc-1.22
Volume:
Proceedings of The Eleventh Dialog System Technology Challenge
Month:
September
Year:
2023
Address:
Prague, Czech Republic
Editors:
Yun-Nung Chen, Paul Crook, Michel Galley, Sarik Ghazarian, Chulaka Gunasekara, Raghav Gupta, Behnam Hedayatnia, Satwik Kottur, Seungwhan Moon, Chen Zhang
Venues:
DSTC | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
193–205
Language:
URL:
https://aclanthology.org/2023.dstc-1.22
DOI:
Bibkey:
Cite (ACL):
Lea Krause, Selene Báez Santamaría, Michiel van der Meer, and Urja Khurana. 2023. Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation. In Proceedings of The Eleventh Dialog System Technology Challenge, pages 193–205, Prague, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation (Krause et al., DSTC-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.dstc-1.22.pdf