@inproceedings{aghajanyan-etal-2019-towards,
title = "Towards Language Agnostic Universal Representations",
author = "Aghajanyan, Armen and
Song, Xia and
Tiwary, Saurabh",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1395",
doi = "10.18653/v1/P19-1395",
pages = "4033--4041",
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. 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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aghajanyan-etal-2019-towards">
<titleInfo>
<title>Towards Language Agnostic Universal Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Armen</namePart>
<namePart type="family">Aghajanyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saurabh</namePart>
<namePart type="family">Tiwary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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. 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.</abstract>
<identifier type="citekey">aghajanyan-etal-2019-towards</identifier>
<identifier type="doi">10.18653/v1/P19-1395</identifier>
<location>
<url>https://aclanthology.org/P19-1395</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>4033</start>
<end>4041</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Language Agnostic Universal Representations
%A Aghajanyan, Armen
%A Song, Xia
%A Tiwary, Saurabh
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F aghajanyan-etal-2019-towards
%X 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. 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.
%R 10.18653/v1/P19-1395
%U https://aclanthology.org/P19-1395
%U https://doi.org/10.18653/v1/P19-1395
%P 4033-4041
Markdown (Informal)
[Towards Language Agnostic Universal Representations](https://aclanthology.org/P19-1395) (Aghajanyan et al., ACL 2019)
ACL
- Armen Aghajanyan, Xia Song, and Saurabh Tiwary. 2019. Towards Language Agnostic Universal Representations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4033–4041, Florence, Italy. Association for Computational Linguistics.