Order-Based Pre-training Strategies for Procedural Text Understanding

Abhilash Nandy, Yash Kulkarni, Pawan Goyal, Niloy Ganguly


Abstract
In this paper, we propose sequence-based pre-training methods to enhance procedural understanding in natural language processing. Procedural text, containing sequential instructions to accomplish a task, is difficult to understand due to the changing attributes of entities in the context. We focus on recipes as they are commonly represented as ordered instructions, and use this order as a supervision signal. Our work is one of the first to compare several ‘order-as-supervision’ transformer pre-training methods, including Permutation Classification, Embedding Regression, and Skip-Clip, and show that these methods give improved results compared to baselines and SoTA LLMs on two downstream Entity-Tracking datasets: NPN-Cooking dataset in recipe domain and ProPara dataset in open domain. Our proposed methods address the non-trivial Entity Tracking Task that requires prediction of entity states across procedure steps, which requires understanding the order of steps. These methods show an improvement over the best baseline by 1.6% and 7-9% on NPN-Cooking and ProPara Datasets respectively across metrics.
Anthology ID:
2024.naacl-short.74
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
821–828
Language:
URL:
https://aclanthology.org/2024.naacl-short.74
DOI:
Bibkey:
Cite (ACL):
Abhilash Nandy, Yash Kulkarni, Pawan Goyal, and Niloy Ganguly. 2024. Order-Based Pre-training Strategies for Procedural Text Understanding. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 821–828, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Order-Based Pre-training Strategies for Procedural Text Understanding (Nandy et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-short.74.pdf