Answers are grounded in this paper and cite their sources.
Current approaches to learning vector representations of text that are compatible between different languages usually require some amount of parallel text, aligned at word, sentence or at least document level. We hypothesize however, that different natural languages share enough semantic structure that it should be possible, in principle, to learn compatible vector representations just by analyzing the monolingual distribution of words.
No takes yet. Share an insight, caveat, or question.
Antonio Valerio Miceli Barone (2016) studied this question.