CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text
This work addresses the challenge of understanding procedural text for NLP applications, showing incremental improvements in domain-specific and open-domain settings.
The paper tackles the problem of learning from procedural text by proposing CLMSM, a multi-task pre-training framework that outperforms baselines on in-domain recipe tasks and generalizes to open-domain procedural NLP tasks.
In this paper, we propose CLMSM, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes. CLMSM uses a Multi-Task Learning Framework to optimize two objectives - a) Contrastive Learning using hard triplets to learn fine-grained differences across entities in the procedures, and b) a novel Mask-Step Modelling objective to learn step-wise context of a procedure. We test the performance of CLMSM on the downstream tasks of tracking entities and aligning actions between two procedures on three datasets, one of which is an open-domain dataset not conforming with the pre-training dataset. We show that CLMSM not only outperforms baselines on recipes (in-domain) but is also able to generalize to open-domain procedural NLP tasks.