@inproceedings{stratos-2017-reconstruction,
    title = "Reconstruction of Word Embeddings from Sub-Word Parameters",
    author = "Stratos, Karl",
    editor = "Faruqui, Manaal  and
      Schuetze, Hinrich  and
      Trancoso, Isabel  and
      Yaghoobzadeh, Yadollah",
    booktitle = "Proceedings of the First Workshop on Subword and Character Level Models in {NLP}",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W17-4119/",
    doi = "10.18653/v1/W17-4119",
    pages = "130--135",
    abstract = "Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is quite simple: before task-specific training, we first optimize sub-word parameters to reconstruct pre-trained word embeddings using various distance measures. We report interesting results on a variety of tasks: word similarity, word analogy, and part-of-speech tagging."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stratos-2017-reconstruction">
    <titleInfo>
        <title>Reconstruction of Word Embeddings from Sub-Word Parameters</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Karl</namePart>
        <namePart type="family">Stratos</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>Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is quite simple: before task-specific training, we first optimize sub-word parameters to reconstruct pre-trained word embeddings using various distance measures. We report interesting results on a variety of tasks: word similarity, word analogy, and part-of-speech tagging.</abstract>
    <identifier type="citekey">stratos-2017-reconstruction</identifier>
    <identifier type="doi">10.18653/v1/W17-4119</identifier>
    <location>
        <url>https://aclanthology.org/W17-4119/</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>130</start>
            <end>135</end>
        </extent>
    </part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reconstruction of Word Embeddings from Sub-Word Parameters
%A Stratos, Karl
%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 stratos-2017-reconstruction
%X Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is quite simple: before task-specific training, we first optimize sub-word parameters to reconstruct pre-trained word embeddings using various distance measures. We report interesting results on a variety of tasks: word similarity, word analogy, and part-of-speech tagging.
%R 10.18653/v1/W17-4119
%U https://aclanthology.org/W17-4119/
%U https://doi.org/10.18653/v1/W17-4119
%P 130-135
Markdown (Informal)
[Reconstruction of Word Embeddings from Sub-Word Parameters](https://aclanthology.org/W17-4119/) (Stratos, SCLeM 2017)
ACL