Abstract
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.- Anthology ID:
- 2023.findings-emnlp.589
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8793–8806
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.589
- DOI:
- 10.18653/v1/2023.findings-emnlp.589
- Cite (ACL):
- Abhilash Nandy, Manav Kapadnis, Pawan Goyal, and Niloy Ganguly. 2023. CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8793–8806, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text (Nandy et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.findings-emnlp.589.pdf