Building Materials Knowledge Models via Document Network Analysis
Anna Hiszpanski | 22-ERD-027
Executive Summary
Our goal is to demonstrate that advances in machine learning for text can be applied to scientific literature to organize and make more accessible the knowledge that is embedded in documents and help generate new hypotheses. By focusing on literature pertaining to conversion of carbon dioxide to value-added products, we believe this work will speed development of new catalysts that reduce carbon emissions.
Publications, Presentations, and Patents
Anna Hiszpanski, Juanita Ordonez, David Buttler, Aditya Prajapti, Huiyun Jeong, “Creating Knowledge Maps from Literature to Accelerate Catalytic CO2 Conversion Development” (Presentation at Spring Materials Research Society Meeting, San Francisco, CA, April 13, 2023).
Jiwoo Choi, Kihoon Bang, Suji Jang, Jaewoong Choi, Juanita Ordonez, David Buttler, Anna Hiszpanski, Thomas Yong-Jin Han, Seok Su Sohn, Byungju Lee, Kwang-Ryeol Lee, Sang Soo Han, Donghun Kim. “Deep Learning of Electrochemical CO2 Conversion Literature Reveals Research Trends and Directions.” J. Mater. Chem. A, 2023, 11, 17628-17643. https://doi.org/10.1039/D3TA02780E
