<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="godin-etal-2018-explaining">
    <titleInfo>
        <title>Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Fréderic</namePart>
        <namePart type="family">Godin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kris</namePart>
        <namePart type="family">Demuynck</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joni</namePart>
        <namePart type="family">Dambre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wesley</namePart>
        <namePart type="family">De Neve</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Demeester</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us to compare convolutional neural networks and bidirectional long short-term memory networks. We evaluate and compare these models for the task of morphological tagging on three morphologically different languages and show that these models implicitly discover understandable linguistic rules.</abstract>
    <identifier type="citekey">godin-etal-2018-explaining</identifier>
    <identifier type="doi">10.18653/v1/D18-1365</identifier>
    <location>
        <url>https://aclanthology.org/D18-1365</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>3275</start>
            <end>3284</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?
%A Godin, Fréderic
%A Demuynck, Kris
%A Dambre, Joni
%A De Neve, Wesley
%A Demeester, Thomas
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F godin-etal-2018-explaining
%X Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us to compare convolutional neural networks and bidirectional long short-term memory networks. We evaluate and compare these models for the task of morphological tagging on three morphologically different languages and show that these models implicitly discover understandable linguistic rules.
%R 10.18653/v1/D18-1365
%U https://aclanthology.org/D18-1365
%U https://doi.org/10.18653/v1/D18-1365
%P 3275-3284

Markdown (Informal)

[Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?](https://aclanthology.org/D18-1365) (Godin et al., EMNLP 2018)

• Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules? (Godin et al., EMNLP 2018)

ACL

• Fréderic Godin, Kris Demuynck, Joni Dambre, Wesley De Neve, and Thomas Demeester. 2018. Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3275–3284, Brussels, Belgium. Association for Computational Linguistics.