Correcting automatic translations through collaborations between MT and monolingual target-language users
Joshua S. Albrecht, Rebecca Hwa, G. Elisabeta Marai · 2009
Machine translation (MT) systems have improved significantly: however, their outputs often contain too many errors to communicate the intended meaning to their users. This paper describes a collaborative approach for mediating between an MT system and users who do not understand the source language and thus cannot easily detect translation mistakes on their own. Through a visualization of multiple linguistic resources, this approach enables the users to correct difficult translation errors and understand translated passages that were otherwise baffling.