Learning Action Conditions from Instructional Manuals for Instruction Understanding
Te-Lin Wu, Caiqi Zhang, Qingyuan Hu, Alexander Spangher, Nanyun Peng
Abstract
The ability to infer pre- and postconditions of an action is vital for comprehending complex instructions, and is essential for applications such as autonomous instruction-guided agents and assistive AI that supports humans to perform physical tasks. In this work, we propose a task dubbed action condition inference, which extracts mentions of preconditions and postconditions of actions in instructional manuals. We propose a weakly supervised approach utilizing automatically constructed large-scale training instances from online instructions, and curate a densely human-annotated and validated dataset to study how well the current NLP models do on the proposed task. We design two types of models differ by whether contextualized and global information is leveraged, as well as various combinations of heuristics to construct the weak supervisions.Our experiments show a > 20% F1-score improvement with considering the entire instruction contexts and a > 6% F1-score benefit with the proposed heuristics. However, the best performing model is still well-behind human performance.- Anthology ID:
- 2023.acl-long.170
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3023–3043
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.170
- DOI:
- 10.18653/v1/2023.acl-long.170
- Cite (ACL):
- Te-Lin Wu, Caiqi Zhang, Qingyuan Hu, Alexander Spangher, and Nanyun Peng. 2023. Learning Action Conditions from Instructional Manuals for Instruction Understanding. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3023–3043, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Learning Action Conditions from Instructional Manuals for Instruction Understanding (Wu et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.170.pdf