<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2017-rotated">
    <titleInfo>
        <title>Rotated Word Vector Representations and their Interpretability</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sungjoon</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">JinYeong</namePart>
        <namePart type="family">Bak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alice</namePart>
        <namePart type="family">Oh</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>Vector representation of words improves performance in various NLP tasks, but the high dimensional word vectors are very difficult to interpret. We apply several rotation algorithms to the vector representation of words to improve the interpretability. Unlike previous approaches that induce sparsity, the rotated vectors are interpretable while preserving the expressive performance of the original vectors. Furthermore, any prebuilt word vector representation can be rotated for improved interpretability. We apply rotation to skipgrams and glove and compare the expressive power and interpretability with the original vectors and the sparse overcomplete vectors. The results show that the rotated vectors outperform the original and the sparse overcomplete vectors for interpretability and expressiveness tasks.</abstract>
    <identifier type="citekey">park-etal-2017-rotated</identifier>
    <identifier type="doi">10.18653/v1/D17-1041</identifier>
    <location>
        <url>https://aclanthology.org/D17-1041</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>401</start>
            <end>411</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Rotated Word Vector Representations and their Interpretability
%A Park, Sungjoon
%A Bak, JinYeong
%A Oh, Alice
%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 park-etal-2017-rotated
%X Vector representation of words improves performance in various NLP tasks, but the high dimensional word vectors are very difficult to interpret. We apply several rotation algorithms to the vector representation of words to improve the interpretability. Unlike previous approaches that induce sparsity, the rotated vectors are interpretable while preserving the expressive performance of the original vectors. Furthermore, any prebuilt word vector representation can be rotated for improved interpretability. We apply rotation to skipgrams and glove and compare the expressive power and interpretability with the original vectors and the sparse overcomplete vectors. The results show that the rotated vectors outperform the original and the sparse overcomplete vectors for interpretability and expressiveness tasks.
%R 10.18653/v1/D17-1041
%U https://aclanthology.org/D17-1041
%U https://doi.org/10.18653/v1/D17-1041
%P 401-411

Markdown (Informal)

[Rotated Word Vector Representations and their Interpretability](https://aclanthology.org/D17-1041) (Park et al., EMNLP 2017)

• Rotated Word Vector Representations and their Interpretability (Park et al., EMNLP 2017)

ACL

• Sungjoon Park, JinYeong Bak, and Alice Oh. 2017. Rotated Word Vector Representations and their Interpretability. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 401–411, Copenhagen, Denmark. Association for Computational Linguistics.