Recent work in learning bilingual representations tend to tailor towards achieving good performance on bilingual tasks, most often the crosslingual document classification (CLDC) evaluation, but to the detriment of preserving clustering structures of word representations monolingually.
No takes yet. Share an insight, caveat, or question.
Luong et al. (2015) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: