<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="horsmann-zesch-2017-lstms">
    <titleInfo>
        <title>Do LSTMs really work so well for PoS tagging? – A replication study</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tobias</namePart>
        <namePart type="family">Horsmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Torsten</namePart>
        <namePart type="family">Zesch</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 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</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>A recent study by Plank et al. (2016) found that LSTM-based PoS taggers considerably improve over the current state-of-the-art when evaluated on the corpora of the Universal Dependencies project that use a coarse-grained tagset. We replicate this study using a fresh collection of 27 corpora of 21 languages that are annotated with fine-grained tagsets of varying size. Our replication confirms the result in general, and we additionally find that the advantage of LSTMs is even bigger for larger tagsets. However, we also find that for the very large tagsets of morphologically rich languages, hand-crafted morphological lexicons are still necessary to reach state-of-the-art performance.</abstract>
    <identifier type="citekey">horsmann-zesch-2017-lstms</identifier>
    <identifier type="doi">10.18653/v1/D17-1076</identifier>
    <location>
        <url>https://aclanthology.org/D17-1076</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>727</start>
            <end>736</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do LSTMs really work so well for PoS tagging? – A replication study
%A Horsmann, Tobias
%A Zesch, Torsten
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F horsmann-zesch-2017-lstms
%X A recent study by Plank et al. (2016) found that LSTM-based PoS taggers considerably improve over the current state-of-the-art when evaluated on the corpora of the Universal Dependencies project that use a coarse-grained tagset. We replicate this study using a fresh collection of 27 corpora of 21 languages that are annotated with fine-grained tagsets of varying size. Our replication confirms the result in general, and we additionally find that the advantage of LSTMs is even bigger for larger tagsets. However, we also find that for the very large tagsets of morphologically rich languages, hand-crafted morphological lexicons are still necessary to reach state-of-the-art performance.
%R 10.18653/v1/D17-1076
%U https://aclanthology.org/D17-1076
%U https://doi.org/10.18653/v1/D17-1076
%P 727-736

Markdown (Informal)

[Do LSTMs really work so well for PoS tagging? – A replication study](https://aclanthology.org/D17-1076) (Horsmann & Zesch, EMNLP 2017)

• Do LSTMs really work so well for PoS tagging? – A replication study (Horsmann & Zesch, EMNLP 2017)

ACL

• Tobias Horsmann and Torsten Zesch. 2017. Do LSTMs really work so well for PoS tagging? – A replication study. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 727–736, Copenhagen, Denmark. Association for Computational Linguistics.