extraction-framework
extraction-framework copied to clipboard
Mapping of the language codes which do not follow ISO-639-1, to a related ISO-639-1 code
In Language.scala there is map for language codes which do not follow ISO-639-1. I think some mapping is not correct. For example, "lez" -> "ru",
Lezgian language mapped to Russian. However, Lezgian language is one of the Lezgic languages which is one of the Northeast_Caucasian_languages. It is more similar to Avar than Russian (I don't think there is similarity between Russian and Lezgian).