Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction

Julia White, Arushi Raghuvanshi, Yada Pruksachatkun


Abstract
Task-oriented dialogues often require agents to enact complex, multi-step procedures in order to meet user requests. While large language models have found success automating these dialogues in constrained environments, their widespread deployment is limited by the substantial quantities of task-specific data required for training. The following paper presents a data-efficient solution to constructing dialogue systems, leveraging explicit instructions derived from agent guidelines, such as company policies or customer service manuals. Our proposed Knowledge-Augmented Dialogue System (KADS) combines a large language model with a knowledge retrieval module that pulls documents outlining relevant procedures from a predefined set of policies, given a user-agent interaction. To train this system, we introduce a semi-supervised pre-training scheme that employs dialogue-document matching and action-oriented masked language modeling with partial parameter freezing. We evaluate the effectiveness of our approach on prominent task-oriented dialogue datasets, Action-Based Conversations Dataset and Schema-Guided Dialogue, for two dialogue tasks: action state tracking and workflow discovery. Our results demonstrate that procedural knowledge augmentation improves accuracy predicting in- and out-of-distribution actions while preserving high performance in settings with low or sparse data.
Anthology ID:
2023.findings-acl.182
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:
2895–2904
Language:
URL:
https://aclanthology.org/2023.findings-acl.182
DOI:
10.18653/v1/2023.findings-acl.182
Bibkey:
Cite (ACL):
Julia White, Arushi Raghuvanshi, and Yada Pruksachatkun. 2023. Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2895–2904, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction (White et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.182.pdf
Video:
 https://aclanthology.org/2023.findings-acl.182.mp4