<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hangya-etal-2022-improving">
    <titleInfo>
        <title>Improving Low-Resource Languages in Pre-Trained Multilingual Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Viktor</namePart>
        <namePart type="family">Hangya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hossain</namePart>
        <namePart type="given">Shaikh</namePart>
        <namePart type="family">Saadi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Fraser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pre-trained multilingual language models are the foundation of many NLP approaches, including cross-lingual transfer solutions. However, languages with small available monolingual corpora are often not well-supported by these models leading to poor performance. We propose an unsupervised approach to improve the cross-lingual representations of low-resource languages by bootstrapping word translation pairs from monolingual corpora and using them to improve language alignment in pre-trained language models. We perform experiments on nine languages, using contextual word retrieval and zero-shot named entity recognition to measure both intrinsic cross-lingual word representation quality and downstream task performance, showing improvements on both tasks. Our results show that it is possible to improve pre-trained multilingual language models by relying only on non-parallel resources.</abstract>
    <identifier type="citekey">hangya-etal-2022-improving</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.822</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.822</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>11993</start>
            <end>12006</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Low-Resource Languages in Pre-Trained Multilingual Language Models
%A Hangya, Viktor
%A Saadi, Hossain Shaikh
%A Fraser, Alexander
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F hangya-etal-2022-improving
%X Pre-trained multilingual language models are the foundation of many NLP approaches, including cross-lingual transfer solutions. However, languages with small available monolingual corpora are often not well-supported by these models leading to poor performance. We propose an unsupervised approach to improve the cross-lingual representations of low-resource languages by bootstrapping word translation pairs from monolingual corpora and using them to improve language alignment in pre-trained language models. We perform experiments on nine languages, using contextual word retrieval and zero-shot named entity recognition to measure both intrinsic cross-lingual word representation quality and downstream task performance, showing improvements on both tasks. Our results show that it is possible to improve pre-trained multilingual language models by relying only on non-parallel resources.
%R 10.18653/v1/2022.emnlp-main.822
%U https://aclanthology.org/2022.emnlp-main.822
%U https://doi.org/10.18653/v1/2022.emnlp-main.822
%P 11993-12006

Markdown (Informal)

[Improving Low-Resource Languages in Pre-Trained Multilingual Language Models](https://aclanthology.org/2022.emnlp-main.822) (Hangya et al., EMNLP 2022)

• Improving Low-Resource Languages in Pre-Trained Multilingual Language Models (Hangya et al., EMNLP 2022)

ACL

• Viktor Hangya, Hossain Shaikh Saadi, and Alexander Fraser. 2022. Improving Low-Resource Languages in Pre-Trained Multilingual Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11993–12006, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.