<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="havard-etal-2019-word">
    <titleInfo>
        <title>Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">William</namePart>
        <namePart type="given">N</namePart>
        <namePart type="family">Havard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-Pierre</namePart>
        <namePart type="family">Chevrot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laurent</namePart>
        <namePart type="family">Besacier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we study how word-like units are represented and activated in a recurrent neural model of visually grounded speech. The model used in our experiments is trained to project an image and its spoken description in a common representation space. We show that a recurrent model trained on spoken sentences implicitly segments its input into word-like units and reliably maps them to their correct visual referents. We introduce a methodology originating from linguistics to analyse the representation learned by neural networks – the gating paradigm – and show that the correct representation of a word is only activated if the network has access to first phoneme of the target word, suggesting that the network does not rely on a global acoustic pattern. Furthermore, we find out that not all speech frames (MFCC vectors in our case) play an equal role in the final encoded representation of a given word, but that some frames have a crucial effect on it. Finally we suggest that word representation could be activated through a process of lexical competition.</abstract>
    <identifier type="citekey">havard-etal-2019-word</identifier>
    <identifier type="doi">10.18653/v1/K19-1032</identifier>
    <location>
        <url>https://aclanthology.org/K19-1032</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>339</start>
            <end>348</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech
%A Havard, William N.
%A Chevrot, Jean-Pierre
%A Besacier, Laurent
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F havard-etal-2019-word
%X In this paper, we study how word-like units are represented and activated in a recurrent neural model of visually grounded speech. The model used in our experiments is trained to project an image and its spoken description in a common representation space. We show that a recurrent model trained on spoken sentences implicitly segments its input into word-like units and reliably maps them to their correct visual referents. We introduce a methodology originating from linguistics to analyse the representation learned by neural networks – the gating paradigm – and show that the correct representation of a word is only activated if the network has access to first phoneme of the target word, suggesting that the network does not rely on a global acoustic pattern. Furthermore, we find out that not all speech frames (MFCC vectors in our case) play an equal role in the final encoded representation of a given word, but that some frames have a crucial effect on it. Finally we suggest that word representation could be activated through a process of lexical competition.
%R 10.18653/v1/K19-1032
%U https://aclanthology.org/K19-1032
%U https://doi.org/10.18653/v1/K19-1032
%P 339-348

Markdown (Informal)

[Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech](https://aclanthology.org/K19-1032) (Havard et al., CoNLL 2019)

• Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech (Havard et al., CoNLL 2019)

ACL

• William N. Havard, Jean-Pierre Chevrot, and Laurent Besacier. 2019. Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 339–348, Hong Kong, China. Association for Computational Linguistics.