<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasan-curry-2017-word">
    <titleInfo>
        <title>Word Re-Embedding via Manifold Dimensionality Retention</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Souleiman</namePart>
        <namePart type="family">Hasan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Edward</namePart>
        <namePart type="family">Curry</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 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</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>Word embeddings seek to recover a Euclidean metric space by mapping words into vectors, starting from words co-occurrences in a corpus. Word embeddings may underestimate the similarity between nearby words, and overestimate it between distant words in the Euclidean metric space. In this paper, we re-embed pre-trained word embeddings with a stage of manifold learning which retains dimensionality. We show that this approach is theoretically founded in the metric recovery paradigm, and empirically show that it can improve on state-of-the-art embeddings in word similarity tasks 0.5 - 5.0% points depending on the original space.</abstract>
    <identifier type="citekey">hasan-curry-2017-word</identifier>
    <identifier type="doi">10.18653/v1/D17-1033</identifier>
    <location>
        <url>https://aclanthology.org/D17-1033</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>321</start>
            <end>326</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Word Re-Embedding via Manifold Dimensionality Retention
%A Hasan, Souleiman
%A Curry, Edward
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F hasan-curry-2017-word
%X Word embeddings seek to recover a Euclidean metric space by mapping words into vectors, starting from words co-occurrences in a corpus. Word embeddings may underestimate the similarity between nearby words, and overestimate it between distant words in the Euclidean metric space. In this paper, we re-embed pre-trained word embeddings with a stage of manifold learning which retains dimensionality. We show that this approach is theoretically founded in the metric recovery paradigm, and empirically show that it can improve on state-of-the-art embeddings in word similarity tasks 0.5 - 5.0% points depending on the original space.
%R 10.18653/v1/D17-1033
%U https://aclanthology.org/D17-1033
%U https://doi.org/10.18653/v1/D17-1033
%P 321-326

Markdown (Informal)

[Word Re-Embedding via Manifold Dimensionality Retention](https://aclanthology.org/D17-1033) (Hasan & Curry, EMNLP 2017)

• Word Re-Embedding via Manifold Dimensionality Retention (Hasan & Curry, EMNLP 2017)

ACL

• Souleiman Hasan and Edward Curry. 2017. Word Re-Embedding via Manifold Dimensionality Retention. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 321–326, Copenhagen, Denmark. Association for Computational Linguistics.