DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles
This addresses the challenge of curating knowledge bases in scientific domains like materials science by extracting structured information from research article tables.
The authors tackled the problem of extracting material compositions from tables in materials science articles, defining a novel NLP task and releasing a dataset of 4,408 distantly supervised tables with 1,475 manually annotated tables, and their DISCOMAT baseline outperformed recent table processing architectures by significant margins.
A crucial component in the curation of KB for a scientific domain (e.g., materials science, foods & nutrition, fuels) is information extraction from tables in the domain's published research articles. To facilitate research in this direction, we define a novel NLP task of extracting compositions of materials (e.g., glasses) from tables in materials science papers. The task involves solving several challenges in concert, such as tables that mention compositions have highly varying structures; text in captions and full paper needs to be incorporated along with data in tables; and regular languages for numbers, chemical compounds and composition expressions must be integrated into the model. We release a training dataset comprising 4,408 distantly supervised tables, along with 1,475 manually annotated dev and test tables. We also present a strong baseline DISCOMAT, that combines multiple graph neural networks with several task-specific regular expressions, features, and constraints. We show that DISCOMAT outperforms recent table processing architectures by significant margins.