AI RESEARCH
Semantic Embeddings of Chemical Elements for Enhanced Materials Inference and Discovery
arXiv CS.LG
•
ArXi:2502.14912v2 Announce Type: replace-cross We present a framework for generating universal semantic embeddings of chemical elements to advance materials inference and discovery. This framework leverages ElementBERT, a domain-specific BERT-based natural language processing model trained on 1.29M abstracts of alloy-related scientific papers, to capture latent knowledge and contextual relationships specific to alloys.