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.
Original language | English |
---|---|
Pages | 193-205 |
Number of pages | 13 |
Publication status | Published - 2023 |
Event | 11th Dialog System Technology Challenge, DSTC 2023 - Prague, Czech Republic Duration: 11 Sept 2023 → … |
Conference
Conference | 11th Dialog System Technology Challenge, DSTC 2023 |
---|---|
Country/Territory | Czech Republic |
City | Prague |
Period | 11/09/23 → … |
Bibliographical note
Publisher Copyright:© 2023 Association for Computational Linguistics.