<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shain-elsner-2020-acquiring">
    <titleInfo>
        <title>Acquiring language from speech by learning to remember and predict</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Cory</namePart>
        <namePart type="family">Shain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Micha</namePart>
        <namePart type="family">Elsner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 24th Conference on Computational Natural Language Learning</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Raquel</namePart>
            <namePart type="family">Fernández</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tal</namePart>
            <namePart type="family">Linzen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Classical accounts of child language learning invoke memory limits as a pressure to discover sparse, language-like representations of speech, while more recent proposals stress the importance of prediction for language learning. In this study, we propose a broad-coverage unsupervised neural network model to test memory and prediction as sources of signal by which children might acquire language directly from the perceptual stream. Our model embodies several likely properties of real-time human cognition: it is strictly incremental, it encodes speech into hierarchically organized labeled segments, it allows interactive top-down and bottom-up information flow, it attempts to model its own sequence of latent representations, and its objective function only recruits local signals that are plausibly supported by human working memory capacity. We show that much phonemic structure is learnable from unlabeled speech on the basis of these local signals. We further show that remembering the past and predicting the future both contribute to the linguistic content of acquired representations, and that these contributions are at least partially complementary.</abstract>
    <identifier type="citekey">shain-elsner-2020-acquiring</identifier>
    <identifier type="doi">10.18653/v1/2020.conll-1.15</identifier>
    <location>
        <url>https://aclanthology.org/2020.conll-1.15</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>195</start>
            <end>214</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Acquiring language from speech by learning to remember and predict
%A Shain, Cory
%A Elsner, Micha
%Y Fernández, Raquel
%Y Linzen, Tal
%S Proceedings of the 24th Conference on Computational Natural Language Learning
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F shain-elsner-2020-acquiring
%X Classical accounts of child language learning invoke memory limits as a pressure to discover sparse, language-like representations of speech, while more recent proposals stress the importance of prediction for language learning. In this study, we propose a broad-coverage unsupervised neural network model to test memory and prediction as sources of signal by which children might acquire language directly from the perceptual stream. Our model embodies several likely properties of real-time human cognition: it is strictly incremental, it encodes speech into hierarchically organized labeled segments, it allows interactive top-down and bottom-up information flow, it attempts to model its own sequence of latent representations, and its objective function only recruits local signals that are plausibly supported by human working memory capacity. We show that much phonemic structure is learnable from unlabeled speech on the basis of these local signals. We further show that remembering the past and predicting the future both contribute to the linguistic content of acquired representations, and that these contributions are at least partially complementary.
%R 10.18653/v1/2020.conll-1.15
%U https://aclanthology.org/2020.conll-1.15
%U https://doi.org/10.18653/v1/2020.conll-1.15
%P 195-214

Markdown (Informal)

[Acquiring language from speech by learning to remember and predict](https://aclanthology.org/2020.conll-1.15) (Shain & Elsner, CoNLL 2020)

• Acquiring language from speech by learning to remember and predict (Shain & Elsner, CoNLL 2020)

ACL

• Cory Shain and Micha Elsner. 2020. Acquiring language from speech by learning to remember and predict. In Proceedings of the 24th Conference on Computational Natural Language Learning, pages 195–214, Online. Association for Computational Linguistics.