Towards Language Agnostic Universal Representations

Armen Aghajanyan, Xia Song, Saurabh Tiwary

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 the models trained on a single language using language agnostic representations achieve very similar accuracies in other languages.

Keywords: universal representations, language agnostic representations, NLP, GAN

TL;DR: By taking inspiration from linguistics, specifically the Universal Grammar hypothesis, we learn language agnostic universal representations which we can utilize to do zero-shot learning across languages.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1809.08510/code)