1 code implementation • 19 Jan 2024 • Luca Foppiano, Guillaume Lambard, Toshiyuki Amagasa, Masashi Ishii
This study is dedicated to assessing the capabilities of large language models (LLMs) such as GPT-3. 5-Turbo, GPT-4, and GPT-4-Turbo in extracting structured information from scientific documents in materials science.
1 code implementation • 19 Sep 2023 • Luca Foppiano, Tomoya Mato, Kensei Terashima, Pedro Ortiz Suarez, Taku Tou, Chikako Sakai, Wei-Sheng Wang, Toshiyuki Amagasa, Yoshihiko Takano, Masashi Ishii
For manual operations, the interface (SuperCon2 interface) is developed to increase efficiency during manual correction by providing a smart interface and an enhanced PDF document viewer.
2 code implementations • 26 Oct 2022 • Luca Foppiano, Pedro Baptista de Castro, Pedro Ortiz Suarez, Kensei Terashima, Yoshihiko Takano, Masashi Ishii
Using Grobid-superconductors, we built SuperCon2, a database of 40324 materials and properties records from 37700 papers.
Ranked #1 on NER on SuperMat
1 code implementation • Document Engineering 2019 • Luca Foppiano, Laurent Romary, Masashi Ishii, Mikiko Tanifuji
Normalised materials characteristics (such as critical temperature, pressure) extracted from scientific literature are a key resource for materials informatics (MI) [9].