<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="levy-etal-2015-improving">
    <titleInfo>
        <title>Improving Distributional Similarity with Lessons Learned from Word Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Omer</namePart>
        <namePart type="family">Levy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoav</namePart>
        <namePart type="family">Goldberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ido</namePart>
        <namePart type="family">Dagan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2015</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>Recent trends suggest that neural-network-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks. We reveal that much of the performance gains of word embeddings are due to certain system design choices and hyperparameter optimizations, rather than the embedding algorithms themselves. Furthermore, we show that these modifications can be transferred to traditional distributional models, yielding similar gains. In contrast to prior reports, we observe mostly local or insignificant performance differences between the methods, with no global advantage to any single approach over the others.</abstract>
    <identifier type="citekey">levy-etal-2015-improving</identifier>
    <identifier type="doi">10.1162/tacl_a_00134</identifier>
    <location>
        <url>https://aclanthology.org/Q15-1016</url>
    </location>
    <part>
        <date>2015</date>
        <detail type="volume"><number>3</number></detail>
        <extent unit="page">
            <start>211</start>
            <end>225</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Improving Distributional Similarity with Lessons Learned from Word Embeddings
%A Levy, Omer
%A Goldberg, Yoav
%A Dagan, Ido
%J Transactions of the Association for Computational Linguistics
%D 2015
%V 3
%I MIT Press
%C Cambridge, MA
%F levy-etal-2015-improving
%X Recent trends suggest that neural-network-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks. We reveal that much of the performance gains of word embeddings are due to certain system design choices and hyperparameter optimizations, rather than the embedding algorithms themselves. Furthermore, we show that these modifications can be transferred to traditional distributional models, yielding similar gains. In contrast to prior reports, we observe mostly local or insignificant performance differences between the methods, with no global advantage to any single approach over the others.
%R 10.1162/tacl_a_00134
%U https://aclanthology.org/Q15-1016
%U https://doi.org/10.1162/tacl_a_00134
%P 211-225

Markdown (Informal)

[Improving Distributional Similarity with Lessons Learned from Word Embeddings](https://aclanthology.org/Q15-1016) (Levy et al., TACL 2015)

• Improving Distributional Similarity with Lessons Learned from Word Embeddings (Levy et al., TACL 2015)

ACL

• Omer Levy, Yoav Goldberg, and Ido Dagan. 2015. Improving Distributional Similarity with Lessons Learned from Word Embeddings. Transactions of the Association for Computational Linguistics, 3:211–225.