Order-Based Pre-training Strategies for Procedural Text Understanding
This work addresses the challenge of entity tracking in procedural text for natural language processing applications, representing an incremental advance with specific gains.
The paper tackled the problem of understanding procedural text, such as recipes, by proposing sequence-based pre-training methods that use order as supervision, resulting in improvements of 1.6% on the NPN-Cooking dataset and 7-9% on the ProPara dataset over baselines.
In this paper, we propose sequence-based pretraining 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, which 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 shows that these methods give improved results compared to the 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.