Could KeyWord Masking Strategy Improve Language Model?

MilkOligoThesaurus, a dataset of mammalian milk oligosaccharide synonyms

“…Several strategies were developed and investigated to exploit external lexical and semantic resources to improve machine learning models. These strategies include thematic masking [1] , named entity recognition by distant supervision [2] , and ontology-based normalization [3] . The biological roles of MOs depend mainly on their structure.…”