<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akyurek-etal-2019-morphological">
    <titleInfo>
        <title>Morphological Analysis Using a Sequence Decoder</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ekin</namePart>
        <namePart type="family">Akyürek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Erenay</namePart>
        <namePart type="family">Dayanık</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Deniz</namePart>
        <namePart type="family">Yuret</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019</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>We introduce Morse, a recurrent encoder-decoder model that produces morphological analyses of each word in a sentence. The encoder turns the relevant information about the word and its context into a fixed size vector representation and the decoder generates the sequence of characters for the lemma followed by a sequence of individual morphological features. We show that generating morphological features individually rather than as a combined tag allows the model to handle rare or unseen tags and to outperform whole-tag models. In addition, generating morphological features as a sequence rather than, for example, an unordered set allows our model to produce an arbitrary number of features that represent multiple inflectional groups in morphologically complex languages. We obtain state-of-the-art results in nine languages of different morphological complexity under low-resource, high-resource, and transfer learning settings. We also introduce TrMor2018, a new high-accuracy Turkish morphology data set. Our Morse implementation and the TrMor2018 data set are available online to support future research.1See https://github.com/ai-ku/Morse.jl for a Morse implementation in Julia/Knet (Yuret, 2016) and https://github.com/ai-ku/TrMor2018 for the new Turkish data set.</abstract>
    <identifier type="citekey">akyurek-etal-2019-morphological</identifier>
    <identifier type="doi">10.1162/tacl_a_00286</identifier>
    <location>
        <url>https://aclanthology.org/Q19-1036</url>
    </location>
    <part>
        <date>2019</date>
        <detail type="volume"><number>7</number></detail>
        <extent unit="page">
            <start>567</start>
            <end>579</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Morphological Analysis Using a Sequence Decoder
%A Akyürek, Ekin
%A Dayanık, Erenay
%A Yuret, Deniz
%J Transactions of the Association for Computational Linguistics
%D 2019
%V 7
%I MIT Press
%C Cambridge, MA
%F akyurek-etal-2019-morphological
%X We introduce Morse, a recurrent encoder-decoder model that produces morphological analyses of each word in a sentence. The encoder turns the relevant information about the word and its context into a fixed size vector representation and the decoder generates the sequence of characters for the lemma followed by a sequence of individual morphological features. We show that generating morphological features individually rather than as a combined tag allows the model to handle rare or unseen tags and to outperform whole-tag models. In addition, generating morphological features as a sequence rather than, for example, an unordered set allows our model to produce an arbitrary number of features that represent multiple inflectional groups in morphologically complex languages. We obtain state-of-the-art results in nine languages of different morphological complexity under low-resource, high-resource, and transfer learning settings. We also introduce TrMor2018, a new high-accuracy Turkish morphology data set. Our Morse implementation and the TrMor2018 data set are available online to support future research.1See https://github.com/ai-ku/Morse.jl for a Morse implementation in Julia/Knet (Yuret, 2016) and https://github.com/ai-ku/TrMor2018 for the new Turkish data set.
%R 10.1162/tacl_a_00286
%U https://aclanthology.org/Q19-1036
%U https://doi.org/10.1162/tacl_a_00286
%P 567-579

Markdown (Informal)

[Morphological Analysis Using a Sequence Decoder](https://aclanthology.org/Q19-1036) (Akyürek et al., TACL 2019)

• Morphological Analysis Using a Sequence Decoder (Akyürek et al., TACL 2019)

ACL

• Ekin Akyürek, Erenay Dayanık, and Deniz Yuret. 2019. Morphological Analysis Using a Sequence Decoder. Transactions of the Association for Computational Linguistics, 7:567–579.