Publications by authors named "David Buttler"
Efficiently extracting data from tables in the scientific literature is pivotal for building large-scale databases. However, the tables reported in materials science papers exist in highly diverse forms; thus, rule-based extractions are an ineffective approach. To overcome this challenge, the study presents MaTableGPT, which is a GPT-based table data extractor from the materials science literature.
View Article and Find Full Text PDFArticle Synopsis
- Nanomaterials have various useful applications, but their synthesis is often a lengthy and complex process, making it hard for researchers to keep up with the information needed for development.
- To address this, scientists created tools to extract and organize data from approximately 35,000 articles about nanomaterials, streamlining the access to synthesis protocols and chemical information.
- The effectiveness of these tools was demonstrated with high accuracy in predicting nanomaterial composition and morphology, as well as analyzing images to assess sizes, ultimately helping researchers find trends and insights for future studies.