<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kann-schutze-2017-unlabeled">
    <titleInfo>
        <title>Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Katharina</namePart>
        <namePart type="family">Kann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hinrich</namePart>
        <namePart type="family">Schütze</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Subword and Character Level Models in NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Manaal</namePart>
            <namePart type="family">Faruqui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hinrich</namePart>
            <namePart type="family">Schuetze</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabel</namePart>
            <namePart type="family">Trancoso</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yadollah</namePart>
            <namePart type="family">Yaghoobzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present a semi-supervised way of training a character-based encoder-decoder recurrent neural network for morphological reinflection—the task of generating one inflected wordform from another. This is achieved by using unlabeled tokens or random strings as training data for an autoencoding task, adapting a network for morphological reinflection, and performing multi-task training. We thus use limited labeled data more effectively, obtaining up to 9.92% improvement over state-of-the-art baselines for 8 different languages.</abstract>
    <identifier type="citekey">kann-schutze-2017-unlabeled</identifier>
    <identifier type="doi">10.18653/v1/W17-4111</identifier>
    <location>
        <url>https://aclanthology.org/W17-4111</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>76</start>
            <end>81</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models
%A Kann, Katharina
%A Schütze, Hinrich
%Y Faruqui, Manaal
%Y Schuetze, Hinrich
%Y Trancoso, Isabel
%Y Yaghoobzadeh, Yadollah
%S Proceedings of the First Workshop on Subword and Character Level Models in NLP
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F kann-schutze-2017-unlabeled
%X We present a semi-supervised way of training a character-based encoder-decoder recurrent neural network for morphological reinflection—the task of generating one inflected wordform from another. This is achieved by using unlabeled tokens or random strings as training data for an autoencoding task, adapting a network for morphological reinflection, and performing multi-task training. We thus use limited labeled data more effectively, obtaining up to 9.92% improvement over state-of-the-art baselines for 8 different languages.
%R 10.18653/v1/W17-4111
%U https://aclanthology.org/W17-4111
%U https://doi.org/10.18653/v1/W17-4111
%P 76-81

Markdown (Informal)

[Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models](https://aclanthology.org/W17-4111) (Kann & Schütze, SCLeM 2017)

• Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models (Kann & Schütze, SCLeM 2017)

ACL

• Katharina Kann and Hinrich Schütze. 2017. Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models. In Proceedings of the First Workshop on Subword and Character Level Models in NLP, pages 76–81, Copenhagen, Denmark. Association for Computational Linguistics.