Towards Language Agnostic Universal Representations
This addresses the issue of language barriers in AI for multilingual applications, offering a novel approach to universal representations.
The paper tackles the problem of language-dependent machine learning representations by proposing a method to learn language-agnostic representations, enabling zero-shot cross-lingual application; it demonstrates that models trained on one language achieve very similar accuracies in other languages.
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 and formalizing Universal Grammar as an optimization process (Chomsky, 2014; Montague, 1970). We demonstrate the capabilities of these representations by showing that the models trained on a single language using language agnostic representations achieve very similar accuracies in other languages.