Answers are grounded in this paper and cite their sources.
We describe the design of an autonomous agent that can teach itself how to translate from a foreign language, by first assembling its own training set, then using it to improve its vocabulary and language model. The key idea is that a Statistical Mac
No takes yet. Share an insight, caveat, or question.
Turchi et al. (2012) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: