“Richard Feynman was fond of giving the following advice on how to be a genius. You have to keep a dozen of your favorite problems constantly present in your mind, although by and large they will lay in a dormant state. Every time you hear or read a new trick or a new result, test it against each of your twelve problems to see whether it helps. Every once in a while there will be a hit, and people will say: ‘How did he do it? He must be a genius!’” Attributed to Gian-Carlo Rota

I’d like to collect problems here that interest me. This list may grow.

MT for Bible Translation?

How can we most helpfully speed up the translation of knowledge into “low-resource” languages? Especially those that literally have no written language at all, let alone reams of text data?

• Unsupervised Machine Translation techniques? Word embeddings. See Ruder, Artetxe, etc.
• Work with existing translation tools and workflows, incrementally training “suggester” models?
• Could we train an audio-to-morpheme model? <— this could be the first step to a “universal translator” that teaches itself new languages. Go to a village, leave the audio recorder running, and just train from there…