<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hashimoto-etal-2016-word">
    <titleInfo>
        <title>Word Embeddings as Metric Recovery in Semantic Spaces</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tatsunori</namePart>
        <namePart type="given">B</namePart>
        <namePart type="family">Hashimoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Alvarez-Melis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tommi</namePart>
        <namePart type="given">S</namePart>
        <namePart type="family">Jaakkola</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016</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>Continuous word representations have been remarkably useful across NLP tasks but remain poorly understood. We ground word embeddings in semantic spaces studied in the cognitive-psychometric literature, taking these spaces as the primary objects to recover. To this end, we relate log co-occurrences of words in large corpora to semantic similarity assessments and show that co-occurrences are indeed consistent with an Euclidean semantic space hypothesis. Framing word embedding as metric recovery of a semantic space unifies existing word embedding algorithms, ties them to manifold learning, and demonstrates that existing algorithms are consistent metric recovery methods given co-occurrence counts from random walks. Furthermore, we propose a simple, principled, direct metric recovery algorithm that performs on par with the state-of-the-art word embedding and manifold learning methods. Finally, we complement recent focus on analogies by constructing two new inductive reasoning datasets—series completion and classification—and demonstrate that word embeddings can be used to solve them as well.</abstract>
    <identifier type="citekey">hashimoto-etal-2016-word</identifier>
    <identifier type="doi">10.1162/tacl_a_00098</identifier>
    <location>
        <url>https://aclanthology.org/Q16-1020</url>
    </location>
    <part>
        <date>2016</date>
        <detail type="volume"><number>4</number></detail>
        <extent unit="page">
            <start>273</start>
            <end>286</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Word Embeddings as Metric Recovery in Semantic Spaces
%A Hashimoto, Tatsunori B.
%A Alvarez-Melis, David
%A Jaakkola, Tommi S.
%J Transactions of the Association for Computational Linguistics
%D 2016
%V 4
%I MIT Press
%C Cambridge, MA
%F hashimoto-etal-2016-word
%X Continuous word representations have been remarkably useful across NLP tasks but remain poorly understood. We ground word embeddings in semantic spaces studied in the cognitive-psychometric literature, taking these spaces as the primary objects to recover. To this end, we relate log co-occurrences of words in large corpora to semantic similarity assessments and show that co-occurrences are indeed consistent with an Euclidean semantic space hypothesis. Framing word embedding as metric recovery of a semantic space unifies existing word embedding algorithms, ties them to manifold learning, and demonstrates that existing algorithms are consistent metric recovery methods given co-occurrence counts from random walks. Furthermore, we propose a simple, principled, direct metric recovery algorithm that performs on par with the state-of-the-art word embedding and manifold learning methods. Finally, we complement recent focus on analogies by constructing two new inductive reasoning datasets—series completion and classification—and demonstrate that word embeddings can be used to solve them as well.
%R 10.1162/tacl_a_00098
%U https://aclanthology.org/Q16-1020
%U https://doi.org/10.1162/tacl_a_00098
%P 273-286

Markdown (Informal)

[Word Embeddings as Metric Recovery in Semantic Spaces](https://aclanthology.org/Q16-1020) (Hashimoto et al., TACL 2016)

• Word Embeddings as Metric Recovery in Semantic Spaces (Hashimoto et al., TACL 2016)

ACL

• Tatsunori B. Hashimoto, David Alvarez-Melis, and Tommi S. Jaakkola. 2016. Word Embeddings as Metric Recovery in Semantic Spaces. Transactions of the Association for Computational Linguistics, 4:273–286.