Google announced late last year that it had applied machine learning to its Google translate service, resulting in a neural network capable of “zero-shot” translation.
Zero-shot is translating phrases for language pairs where no explicit training or mapping exists. The trained neural network surprised researchers when it evidence of an interlingua emerged as a path for translating previously unpaired languages and phrase. Researchers indicated that data visualizations of the new system in action provided early evidence of shared semantic representations or interlingua between languages. This is presented as evidence of the neural network generating it’s own procedures for more efficient translation all by itself.
Google Translate trajectory over the past 10 years is from a few languages to 103 supported languages, translating over 140 billion languages per day. Motivations for implementing neural network to improve accuracy and efficiency are the many successes of neural network application in other fields.
A key question presented in the findings is whether or not one can translate between a language pair that hadn’t been paired before, but might have some secondary path connecting them, for example English to Korean, Korean to Japanese, and then inferencing English to Japanese.
