Abstract
When a bilingual student learns to solve word
problems in math, we expect the student to
be able to solve these problem in both languages the student is fluent in, even if the math
lessons were only taught in one language.
However, current representations in machine
learning are language dependent. In this work,
we present a method to decouple the language
from the problem by learning language agnostic representations and therefore allowing
training a model in one language and applying to a different one in a zero shot fashion.
We learn these representations by taking inspiration from linguistics, specifically the Universal Grammar hypothesis and learn universal latent representations that are language agnostic (Chomsky, 2014; Montague, 1970). We
demonstrate the capabilities of these representations by showing that models trained on a
single language using language agnostic representations achieve very similar accuracies in
other languages.