<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakuma-yoshinaga-2019-multilingual">
    <titleInfo>
        <title>Multilingual Model Using Cross-Task Embedding Projection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jin</namePart>
        <namePart type="family">Sakuma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Naoki</namePart>
        <namePart type="family">Yoshinaga</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 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</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>We present a method for applying a neural network trained on one (resource-rich) language for a given task to other (resource-poor) languages. We accomplish this by inducing a mapping from pre-trained cross-lingual word embeddings to the embedding layer of the neural network trained on the resource-rich language. To perform element-wise cross-task embedding projection, we invent locally linear mapping which assumes and preserves the local topology across the semantic spaces before and after the projection. Experimental results on topic classification task and sentiment analysis task showed that the fully task-specific multilingual model obtained using our method outperformed the existing multilingual models with embedding layers fixed to pre-trained cross-lingual word embeddings.</abstract>
    <identifier type="citekey">sakuma-yoshinaga-2019-multilingual</identifier>
    <identifier type="doi">10.18653/v1/K19-1003</identifier>
    <location>
        <url>https://aclanthology.org/K19-1003</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>22</start>
            <end>32</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual Model Using Cross-Task Embedding Projection
%A Sakuma, Jin
%A Yoshinaga, Naoki
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F sakuma-yoshinaga-2019-multilingual
%X We present a method for applying a neural network trained on one (resource-rich) language for a given task to other (resource-poor) languages. We accomplish this by inducing a mapping from pre-trained cross-lingual word embeddings to the embedding layer of the neural network trained on the resource-rich language. To perform element-wise cross-task embedding projection, we invent locally linear mapping which assumes and preserves the local topology across the semantic spaces before and after the projection. Experimental results on topic classification task and sentiment analysis task showed that the fully task-specific multilingual model obtained using our method outperformed the existing multilingual models with embedding layers fixed to pre-trained cross-lingual word embeddings.
%R 10.18653/v1/K19-1003
%U https://aclanthology.org/K19-1003
%U https://doi.org/10.18653/v1/K19-1003
%P 22-32

Markdown (Informal)

[Multilingual Model Using Cross-Task Embedding Projection](https://aclanthology.org/K19-1003) (Sakuma & Yoshinaga, CoNLL 2019)

• Multilingual Model Using Cross-Task Embedding Projection (Sakuma & Yoshinaga, CoNLL 2019)

ACL

• Jin Sakuma and Naoki Yoshinaga. 2019. Multilingual Model Using Cross-Task Embedding Projection. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 22–32, Hong Kong, China. Association for Computational Linguistics.