Guided decoding with "enhanced" keyterms

[johnml1135]

By using some combination of alignments, LLM's and Levenshtein distance, we should be able to determine the "proper form" of keywords in the target sentence, and tell NLLB-200 to include that specific surface form of the word. This could be done by doing the following:

1. Determining the matching of proper names for each verse from source to target
2. Giving this information to an LLM to say "when this word is used here in this context, the surface form looks like this" - give it a lot of examples. Put them in the context window
3. Ask the LLM: "For this new name in this context, what should the surface form be?"
4. Take those surface forms and feed them to the LLM to "guide" the decoding.

Implementing this relies upon the successful implementation of #178.

[benjaminking]

This paper has a potentially relevant strategy for picking the correct form of a word to insert:

https://arxiv.org/abs/2107.00334