<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rocha-lopes-cardoso-2019-comparative">
    <titleInfo>
        <title>A Comparative Analysis of Unsupervised Language Adaptation Methods</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gil</namePart>
        <namePart type="family">Rocha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Henrique</namePart>
        <namePart type="family">Lopes Cardoso</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Colin</namePart>
            <namePart type="family">Cherry</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Greg</namePart>
            <namePart type="family">Durrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">George</namePart>
            <namePart type="family">Foster</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Reza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shahram</namePart>
            <namePart type="family">Khadivi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nanyun</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xiang</namePart>
            <namePart type="family">Ren</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Swabha</namePart>
            <namePart type="family">Swayamdipta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>To overcome the lack of annotated resources in less-resourced languages, recent approaches have been proposed to perform unsupervised language adaptation. In this paper, we explore three recent proposals: Adversarial Training, Sentence Encoder Alignment and Shared-Private Architecture. We highlight the differences of these approaches in terms of unlabeled data requirements and capability to overcome additional domain shift in the data. A comparative analysis in two different tasks is conducted, namely on Sentiment Classification and Natural Language Inference. We show that adversarial training methods are more suitable when the source and target language datasets contain other variations in content besides the language shift. Otherwise, sentence encoder alignment methods are very effective and can yield scores on the target language that are close to the source language scores.</abstract>
    <identifier type="citekey">rocha-lopes-cardoso-2019-comparative</identifier>
    <identifier type="doi">10.18653/v1/D19-6102</identifier>
    <location>
        <url>https://aclanthology.org/D19-6102</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>11</start>
            <end>21</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Comparative Analysis of Unsupervised Language Adaptation Methods
%A Rocha, Gil
%A Lopes Cardoso, Henrique
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F rocha-lopes-cardoso-2019-comparative
%X To overcome the lack of annotated resources in less-resourced languages, recent approaches have been proposed to perform unsupervised language adaptation. In this paper, we explore three recent proposals: Adversarial Training, Sentence Encoder Alignment and Shared-Private Architecture. We highlight the differences of these approaches in terms of unlabeled data requirements and capability to overcome additional domain shift in the data. A comparative analysis in two different tasks is conducted, namely on Sentiment Classification and Natural Language Inference. We show that adversarial training methods are more suitable when the source and target language datasets contain other variations in content besides the language shift. Otherwise, sentence encoder alignment methods are very effective and can yield scores on the target language that are close to the source language scores.
%R 10.18653/v1/D19-6102
%U https://aclanthology.org/D19-6102
%U https://doi.org/10.18653/v1/D19-6102
%P 11-21

Markdown (Informal)

[A Comparative Analysis of Unsupervised Language Adaptation Methods](https://aclanthology.org/D19-6102) (Rocha & Lopes Cardoso, 2019)

• A Comparative Analysis of Unsupervised Language Adaptation Methods (Rocha & Lopes Cardoso, 2019)

ACL

• Gil Rocha and Henrique Lopes Cardoso. 2019. A Comparative Analysis of Unsupervised Language Adaptation Methods. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 11–21, Hong Kong, China. Association for Computational Linguistics.