<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rogers-etal-2018-whats">
    <titleInfo>
        <title>What’s in Your Embedding, And How It Predicts Task Performance</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Rogers</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shashwath</namePart>
        <namePart type="family">Hosur Ananthakrishna</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Rumshisky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 27th International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Bender</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leon</namePart>
            <namePart type="family">Derczynski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Pierre</namePart>
            <namePart type="family">Isabelle</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Attempts to find a single technique for general-purpose intrinsic evaluation of word embeddings have so far not been successful. We present a new approach based on scaled-up qualitative analysis of word vector neighborhoods that quantifies interpretable characteristics of a given model (e.g. its preference for synonyms or shared morphological forms as nearest neighbors). We analyze 21 such factors and show how they correlate with performance on 14 extrinsic and intrinsic task datasets (and also explain the lack of correlation between some of them). Our approach enables multi-faceted evaluation, parameter search, and generally – a more principled, hypothesis-driven approach to development of distributional semantic representations.</abstract>
    <identifier type="citekey">rogers-etal-2018-whats</identifier>
    <location>
        <url>https://aclanthology.org/C18-1228/</url>
    </location>
    <part>
        <date>2018-08</date>
        <extent unit="page">
            <start>2690</start>
            <end>2703</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T What’s in Your Embedding, And How It Predicts Task Performance
%A Rogers, Anna
%A Hosur Ananthakrishna, Shashwath
%A Rumshisky, Anna
%Y Bender, Emily M.
%Y Derczynski, Leon
%Y Isabelle, Pierre
%S Proceedings of the 27th International Conference on Computational Linguistics
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F rogers-etal-2018-whats
%X Attempts to find a single technique for general-purpose intrinsic evaluation of word embeddings have so far not been successful. We present a new approach based on scaled-up qualitative analysis of word vector neighborhoods that quantifies interpretable characteristics of a given model (e.g. its preference for synonyms or shared morphological forms as nearest neighbors). We analyze 21 such factors and show how they correlate with performance on 14 extrinsic and intrinsic task datasets (and also explain the lack of correlation between some of them). Our approach enables multi-faceted evaluation, parameter search, and generally – a more principled, hypothesis-driven approach to development of distributional semantic representations.
%U https://aclanthology.org/C18-1228/
%P 2690-2703

Markdown (Informal)

[What’s in Your Embedding, And How It Predicts Task Performance](https://aclanthology.org/C18-1228/) (Rogers et al., COLING 2018)

• What’s in Your Embedding, And How It Predicts Task Performance (Rogers et al., COLING 2018)

ACL

• Anna Rogers, Shashwath Hosur Ananthakrishna, and Anna Rumshisky. 2018. What’s in Your Embedding, And How It Predicts Task Performance. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2690–2703, Santa Fe, New Mexico, USA. Association for Computational Linguistics.