English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent times, transformer networks have achieved state-of-the-artperformance in a wide range of natural language processing tasks. Here wepresent a workflow based on the fine-tuning of BERT models for differentdownstream tasks, which results in the automated extraction of structuredinformation from unstructured natural language in scientific literature.Contrary to existing methods for the automated extraction of structuredcompound-property relations from similar sources, our workflow does not rely onthe definition of intricate grammar rules. Hence, it can be adapted to a newtask without requiring extensive implementation efforts and knowledge. We testour data-extraction workflow by automatically generating a database for Curietemperatures and one for band gaps. These are then compared withmanually-curated datasets and with those obtained with a state-of-the-artrule-based method. Furthermore, in order to showcase the practical utility ofthe automatically extracted data in a material-design workflow, we employ themto construct machine-learning models to predict Curie temperatures and bandgaps. In general we find that, although more noisy, automatically extracteddatasets can grow fast in volume and that such volume partially compensates forthe inaccuracy in downstream tasks.

A rule-free workflow for the automated generation of databases from scientific literature