<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-gaspers-2019-cross">
    <titleInfo>
        <title>Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Quynh</namePart>
        <namePart type="family">Do</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Judith</namePart>
        <namePart type="family">Gaspers</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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jing</namePart>
            <namePart type="family">Jiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vincent</namePart>
            <namePart type="family">Ng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xiaojun</namePart>
            <namePart type="family">Wan</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>A typical cross-lingual transfer learning approach boosting model performance on a language is to pre-train the model on all available supervised data from another language. However, in large-scale systems this leads to high training times and computational requirements. In addition, characteristic differences between the source and target languages raise a natural question of whether source data selection can improve the knowledge transfer. In this paper, we address this question and propose a simple but effective language model based source-language data selection method for cross-lingual transfer learning in large-scale spoken language understanding. The experimental results show that with data selection i) source data and hence training speed is reduced significantly and ii) model performance is improved.</abstract>
    <identifier type="citekey">do-gaspers-2019-cross</identifier>
    <identifier type="doi">10.18653/v1/D19-1153</identifier>
    <location>
        <url>https://aclanthology.org/D19-1153</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>1455</start>
            <end>1460</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding
%A Do, Quynh
%A Gaspers, Judith
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F do-gaspers-2019-cross
%X A typical cross-lingual transfer learning approach boosting model performance on a language is to pre-train the model on all available supervised data from another language. However, in large-scale systems this leads to high training times and computational requirements. In addition, characteristic differences between the source and target languages raise a natural question of whether source data selection can improve the knowledge transfer. In this paper, we address this question and propose a simple but effective language model based source-language data selection method for cross-lingual transfer learning in large-scale spoken language understanding. The experimental results show that with data selection i) source data and hence training speed is reduced significantly and ii) model performance is improved.
%R 10.18653/v1/D19-1153
%U https://aclanthology.org/D19-1153
%U https://doi.org/10.18653/v1/D19-1153
%P 1455-1460

Markdown (Informal)

[Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding](https://aclanthology.org/D19-1153) (Do & Gaspers, EMNLP-IJCNLP 2019)

• Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding (Do & Gaspers, EMNLP-IJCNLP 2019)

ACL

• Quynh Do and Judith Gaspers. 2019. Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1455–1460, Hong Kong, China. Association for Computational Linguistics.