I'm working in a project and stucked in a NLP problem. I'm dealing specially with measure unities in Portuguese (Brazilian) and some parts of my sentences have informal abbreviations. The objective is determine which is the associated unity. I believe it could be solved with a dataset of informal synonymous, but I have no idea of where to find it.

Examples:

Liter --> pt-br -> (Formal) Litro : Abbreviation (L)

Informal: Ltr, Lt