Very impressive! We published something similar recently where we looked at patents and conference proceedings, with a specific focus on texts about energetic materials (explosives and propellants). We showed how chemical-application & chemical-property relations are captured by word2vec and GloVe. For instance we found rocket fuels where the chemicals appearing closest to “rocket” while materials used in air bags appeared closest to “air bag”. We were able to filter to chemical names using ChemDataExtractor and further to likely energetic chemicals by obtaining SMILES strings from PubChem and using a classifier to classify them as likely energetics or not. You can find our work here : https://arxiv.org/pdf/1903.00415.pdf .

I am no longer at UMD but I am helping my collaborators there on a follow up work and we are drawing some encouragement and inspiration from your work — I’ll keep you posted when it is published!