Eric Chagnon

Eric Chagnon is a Computer Systems Engineer with the Center for Advanced Mathematics for Energy Research Applications (CAMERA). He received in B.S in Computation Modeling and Data Analytics from Virginia Tech, and his M.S in Statistics from UC Davis. His research interests include applying natural language processing and deep learning techniques to traditional science and operational problems within LBNL and the DOE. His recent work has focused on pre-training and fine tuning LLMs for epidemiological and organic chemistry problems.

Selected publications:

Chagnon, Pandolfi, Donatelli, and Ushizima, “Benchmarking topic models on scientific articles using BERTeley”, Elsevier NLP, 2024 Volume 6.

Ushizima and Chagnon, "From Gutenberg to BERT: How transformers can change information extraction from text", CMStatistics, King's College, London Dec 2022.