<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kiperwasser-ballesteros-2018-scheduled">
    <titleInfo>
        <title>Scheduled Multi-Task Learning: From Syntax to Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Eliyahu</namePart>
        <namePart type="family">Kiperwasser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Miguel</namePart>
        <namePart type="family">Ballesteros</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework in which our model begins learning syntax and translation interleaved, gradually putting more focus on translation. Using this approach, we achieve considerable improvements in terms of BLEU score on relatively large parallel corpus (WMT14 English to German) and a low-resource (WIT German to English) setup.</abstract>
    <identifier type="citekey">kiperwasser-ballesteros-2018-scheduled</identifier>
    <identifier type="doi">10.1162/tacl_a_00017</identifier>
    <location>
        <url>https://aclanthology.org/Q18-1017</url>
    </location>
    <part>
        <date>2018</date>
        <detail type="volume"><number>6</number></detail>
        <extent unit="page">
            <start>225</start>
            <end>240</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Scheduled Multi-Task Learning: From Syntax to Translation
%A Kiperwasser, Eliyahu
%A Ballesteros, Miguel
%J Transactions of the Association for Computational Linguistics
%D 2018
%V 6
%I MIT Press
%C Cambridge, MA
%F kiperwasser-ballesteros-2018-scheduled
%X Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework in which our model begins learning syntax and translation interleaved, gradually putting more focus on translation. Using this approach, we achieve considerable improvements in terms of BLEU score on relatively large parallel corpus (WMT14 English to German) and a low-resource (WIT German to English) setup.
%R 10.1162/tacl_a_00017
%U https://aclanthology.org/Q18-1017
%U https://doi.org/10.1162/tacl_a_00017
%P 225-240

Markdown (Informal)

[Scheduled Multi-Task Learning: From Syntax to Translation](https://aclanthology.org/Q18-1017) (Kiperwasser & Ballesteros, TACL 2018)

• Scheduled Multi-Task Learning: From Syntax to Translation (Kiperwasser & Ballesteros, TACL 2018)

ACL

• Eliyahu Kiperwasser and Miguel Ballesteros. 2018. Scheduled Multi-Task Learning: From Syntax to Translation. Transactions of the Association for Computational Linguistics, 6:225–240.