<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vania-lopez-2017-characters">
    <titleInfo>
        <title>From Characters to Words to in Between: Do We Capture Morphology?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Clara</namePart>
        <namePart type="family">Vania</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Lopez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they have not been systematically compared, and it is not understood how they interact with different morphological typologies. On a language modeling task, we present experiments that systematically vary (1) the basic unit of representation, (2) the composition of these representations, and (3) the morphological typology of the language modeled. Our results extend previous findings that character representations are effective across typologies, and we find that a previously unstudied combination of character trigram representations composed with bi-LSTMs outperforms most others. But we also find room for improvement: none of the character-level models match the predictive accuracy of a model with access to true morphological analyses, even when learned from an order of magnitude more data.</abstract>
    <identifier type="citekey">vania-lopez-2017-characters</identifier>
    <identifier type="doi">10.18653/v1/P17-1184</identifier>
    <location>
        <url>https://aclanthology.org/P17-1184</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>2016</start>
            <end>2027</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From Characters to Words to in Between: Do We Capture Morphology?
%A Vania, Clara
%A Lopez, Adam
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F vania-lopez-2017-characters
%X Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they have not been systematically compared, and it is not understood how they interact with different morphological typologies. On a language modeling task, we present experiments that systematically vary (1) the basic unit of representation, (2) the composition of these representations, and (3) the morphological typology of the language modeled. Our results extend previous findings that character representations are effective across typologies, and we find that a previously unstudied combination of character trigram representations composed with bi-LSTMs outperforms most others. But we also find room for improvement: none of the character-level models match the predictive accuracy of a model with access to true morphological analyses, even when learned from an order of magnitude more data.
%R 10.18653/v1/P17-1184
%U https://aclanthology.org/P17-1184
%U https://doi.org/10.18653/v1/P17-1184
%P 2016-2027

Markdown (Informal)

[From Characters to Words to in Between: Do We Capture Morphology?](https://aclanthology.org/P17-1184) (Vania & Lopez, ACL 2017)

• From Characters to Words to in Between: Do We Capture Morphology? (Vania & Lopez, ACL 2017)

ACL

• Clara Vania and Adam Lopez. 2017. From Characters to Words to in Between: Do We Capture Morphology?. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2016–2027, Vancouver, Canada. Association for Computational Linguistics.