Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain

Annerose Eichel, Helena Schlipf, Sabine Schulte im Walde


Abstract
We propose a novel approach to learn domain-specific plausible materials for components in the vehicle repair domain by probing Pretrained Language Models (PLMs) in a cloze task style setting to overcome the lack of annotated datasets. We devise a new method to aggregate salient predictions from a set of cloze query templates and show that domain-adaptation using either a small, high-quality or a customized Wikipedia corpus boosts performance. When exploring resource-lean alternatives, we find a distilled PLM clearly outperforming a classic pattern-based algorithm. Further, given that 98% of our domain-specific components are multiword expressions, we successfully exploit the compositionality assumption as a way to address data sparsity.
Anthology ID:
2023.eacl-main.104
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1420–1435
Language:
URL:
https://aclanthology.org/2023.eacl-main.104
DOI:
10.18653/v1/2023.eacl-main.104
Bibkey:
Cite (ACL):
Annerose Eichel, Helena Schlipf, and Sabine Schulte im Walde. 2023. Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1420–1435, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain (Eichel et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.104.pdf
Video:
 https://aclanthology.org/2023.eacl-main.104.mp4