Attribute Controlled Dialogue Prompting

Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart


Abstract
Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data samples within a task, neglecting the fact that inputs vary greatly in some tasks such as open-domain dialogue generation. In this paper, we present a novel, instance-specific prompt-tuning algorithm for dialogue generation. Specifically, we generate prompts based on instance-level control code, rather than the conversation history, to explore their impact on controlled dialogue generation. Experiments on popular open-domain dialogue datasets, evaluated on both automated metrics and human evaluation, demonstrate that our method is superior to prompting baselines and comparable to fine-tuning with only 5%-6% of total parameters.
Anthology ID:
2023.findings-acl.150
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2380–2389
Language:
URL:
https://aclanthology.org/2023.findings-acl.150
DOI:
10.18653/v1/2023.findings-acl.150
Bibkey:
Cite (ACL):
Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, and Pascal Poupart. 2023. Attribute Controlled Dialogue Prompting. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2380–2389, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Attribute Controlled Dialogue Prompting (Liu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2023.findings-acl.150.pdf