L+M-24: Building a Dataset for Language+Molecules @ ACL 2024

Carl Edwards, Qingyun Wang, Lawrence Zhao, Heng Ji


Abstract
Language-molecule models have emerged as an exciting direction for molecular discovery and understanding. However, training these models is challenging due to the scarcity of molecule-language pair datasets. At this point, datasets have been released which are 1) small and scraped from existing databases, 2) large but noisy and constructed by performing entity linking on the scientific literature, and 3) built by converting property prediction datasets to natural language using templates. In this document, we detail the L+M-24 dataset, which has been created for the Language + Molecules Workshop shared task at ACL 2024. In particular, L+M-24 is designed to focus on three key benefits of natural language in molecule design: compositionality, functionality, and abstraction
Anthology ID:
2024.langmol-1.1
Original:
2024.langmol-1.1v1
Version 2:
2024.langmol-1.1v2
Volume:
Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Carl Edwards, Qingyun Wang, Manling Li, Lawrence Zhao, Tom Hope, Heng Ji
Venues:
LangMol | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–9
Language:
URL:
https://aclanthology.org/2024.langmol-1.1
DOI:
10.18653/v1/2024.langmol-1.1
Bibkey:
Cite (ACL):
Carl Edwards, Qingyun Wang, Lawrence Zhao, and Heng Ji. 2024. L+M-24: Building a Dataset for Language+Molecules @ ACL 2024. In Proceedings of the 1st Workshop on Language + Molecules (L+M 2024), pages 1–9, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
L+M-24: Building a Dataset for Language+Molecules @ ACL 2024 (Edwards et al., LangMol-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.langmol-1.1.pdf