@inproceedings{fazili-jyothi-2022-aligning,
title = "Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding",
author = "Fazili, Barah and
Jyothi, Preethi",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.375",
pages = "4268--4273",
abstract = "Multilingual pretrained models, while effective on monolingual data, need additional training to work well with code-switched text. In this work, we present a novel idea of training multilingual models with alignment objectives using parallel text so as to explicitly align word representations with the same underlying semantics across languages. Such an explicit alignment step has a positive downstream effect and improves performance on multiple code-switched NLP tasks. We explore two alignment strategies and report improvements of up to 7.32{\%}, 0.76{\%} and 1.9{\%} on Hindi-English Sentiment Analysis, Named Entity Recognition and Question Answering tasks compared to a competitive baseline model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fazili-jyothi-2022-aligning">
<titleInfo>
<title>Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barah</namePart>
<namePart type="family">Fazili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual pretrained models, while effective on monolingual data, need additional training to work well with code-switched text. In this work, we present a novel idea of training multilingual models with alignment objectives using parallel text so as to explicitly align word representations with the same underlying semantics across languages. Such an explicit alignment step has a positive downstream effect and improves performance on multiple code-switched NLP tasks. We explore two alignment strategies and report improvements of up to 7.32%, 0.76% and 1.9% on Hindi-English Sentiment Analysis, Named Entity Recognition and Question Answering tasks compared to a competitive baseline model.</abstract>
<identifier type="citekey">fazili-jyothi-2022-aligning</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.375</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4268</start>
<end>4273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding
%A Fazili, Barah
%A Jyothi, Preethi
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F fazili-jyothi-2022-aligning
%X Multilingual pretrained models, while effective on monolingual data, need additional training to work well with code-switched text. In this work, we present a novel idea of training multilingual models with alignment objectives using parallel text so as to explicitly align word representations with the same underlying semantics across languages. Such an explicit alignment step has a positive downstream effect and improves performance on multiple code-switched NLP tasks. We explore two alignment strategies and report improvements of up to 7.32%, 0.76% and 1.9% on Hindi-English Sentiment Analysis, Named Entity Recognition and Question Answering tasks compared to a competitive baseline model.
%U https://aclanthology.org/2022.coling-1.375
%P 4268-4273
Markdown (Informal)
[Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding](https://aclanthology.org/2022.coling-1.375) (Fazili & Jyothi, COLING 2022)
ACL