Machine translation locking using sequence-based lock/unlock classification

A computing system, comprising:

• context-dependent token lock classifier logic that receives a representation of a software input string to be translated and classifies tokens in the representation of the software input string to identify a token to be locked for translation, and that generates a classified string, based on the representation of the software input string, with a classification indicator indicating that the identified token is to be locked for translation;
• string conversion logic that converts the classified string into a converted string in which the identified token is identified so that it is locked for translation, based on the classification indicator, and that sends the converted string to a machine translation system;
• and
• unlocking logic that receives a machine translation result from the machine translation system and generates a translated software string, in which the identified token is untranslated, based on the machine translation result.