<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="herbelot-baroni-2017-high">
    <titleInfo>
        <title>High-risk learning: acquiring new word vectors from tiny data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aurélie</namePart>
        <namePart type="family">Herbelot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marco</namePart>
        <namePart type="family">Baroni</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>Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn ‘a good vector’ for a word, a model must have sufficient examples of its usage. This contradicts the fact that humans can guess the meaning of a word from a few occurrences only. In this paper, we show that a neural language model such as Word2Vec only necessitates minor modifications to its standard architecture to learn new terms from tiny data, using background knowledge from a previously learnt semantic space. We test our model on word definitions and on a nonce task involving 2-6 sentences’ worth of context, showing a large increase in performance over state-of-the-art models on the definitional task.</abstract>
    <identifier type="citekey">herbelot-baroni-2017-high</identifier>
    <identifier type="doi">10.18653/v1/D17-1030</identifier>
    <location>
        <url>https://aclanthology.org/D17-1030</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>304</start>
            <end>309</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T High-risk learning: acquiring new word vectors from tiny data
%A Herbelot, Aurélie
%A Baroni, Marco
%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 herbelot-baroni-2017-high
%X Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn ‘a good vector’ for a word, a model must have sufficient examples of its usage. This contradicts the fact that humans can guess the meaning of a word from a few occurrences only. In this paper, we show that a neural language model such as Word2Vec only necessitates minor modifications to its standard architecture to learn new terms from tiny data, using background knowledge from a previously learnt semantic space. We test our model on word definitions and on a nonce task involving 2-6 sentences’ worth of context, showing a large increase in performance over state-of-the-art models on the definitional task.
%R 10.18653/v1/D17-1030
%U https://aclanthology.org/D17-1030
%U https://doi.org/10.18653/v1/D17-1030
%P 304-309

Markdown (Informal)

[High-risk learning: acquiring new word vectors from tiny data](https://aclanthology.org/D17-1030) (Herbelot & Baroni, EMNLP 2017)

• High-risk learning: acquiring new word vectors from tiny data (Herbelot & Baroni, EMNLP 2017)

ACL

• Aurélie Herbelot and Marco Baroni. 2017. High-risk learning: acquiring new word vectors from tiny data. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 304–309, Copenhagen, Denmark. Association for Computational Linguistics.