@inproceedings{weber-colunga-2022-representing,
title = "Representing the Toddler Lexicon: Do the Corpus and Semantics Matter?",
author = "Weber, Jennifer and
Colunga, Eliana",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.421/",
pages = "3960--3968",
abstract = "Understanding child language development requires accurately representing children`s lexicons. However, much of the past work modeling children`s vocabulary development has utilized adult-based measures. The present investigation asks whether using corpora that captures the language input of young children more accurately represents children`s vocabulary knowledge. We present a newly-created toddler corpus that incorporates transcripts of child-directed conversations, the text of picture books written for preschoolers, and dialog from G-rated movies to approximate the language input a North American preschooler might hear. We evaluate the utility of the new corpus for modeling children`s vocabulary development by building and analyzing different semantic network models and comparing them to norms based on vocabulary norms for toddlers in this age range. More specifically, the relations between words in our semantic networks were derived from skip-gram neural networks (Word2Vec) trained on our toddler corpus or on Google news. Results revealed that the models built from the toddler corpus were more accurate at predicting toddler vocabulary growth than the adult-based corpus. These results speak to the importance of selecting a corpus that matches the population of interest."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weber-colunga-2022-representing">
<titleInfo>
<title>Representing the Toddler Lexicon: Do the Corpus and Semantics Matter?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Weber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliana</namePart>
<namePart type="family">Colunga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding child language development requires accurately representing children‘s lexicons. However, much of the past work modeling children‘s vocabulary development has utilized adult-based measures. The present investigation asks whether using corpora that captures the language input of young children more accurately represents children‘s vocabulary knowledge. We present a newly-created toddler corpus that incorporates transcripts of child-directed conversations, the text of picture books written for preschoolers, and dialog from G-rated movies to approximate the language input a North American preschooler might hear. We evaluate the utility of the new corpus for modeling children‘s vocabulary development by building and analyzing different semantic network models and comparing them to norms based on vocabulary norms for toddlers in this age range. More specifically, the relations between words in our semantic networks were derived from skip-gram neural networks (Word2Vec) trained on our toddler corpus or on Google news. Results revealed that the models built from the toddler corpus were more accurate at predicting toddler vocabulary growth than the adult-based corpus. These results speak to the importance of selecting a corpus that matches the population of interest.</abstract>
<identifier type="citekey">weber-colunga-2022-representing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.421/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3960</start>
<end>3968</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Representing the Toddler Lexicon: Do the Corpus and Semantics Matter?
%A Weber, Jennifer
%A Colunga, Eliana
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F weber-colunga-2022-representing
%X Understanding child language development requires accurately representing children‘s lexicons. However, much of the past work modeling children‘s vocabulary development has utilized adult-based measures. The present investigation asks whether using corpora that captures the language input of young children more accurately represents children‘s vocabulary knowledge. We present a newly-created toddler corpus that incorporates transcripts of child-directed conversations, the text of picture books written for preschoolers, and dialog from G-rated movies to approximate the language input a North American preschooler might hear. We evaluate the utility of the new corpus for modeling children‘s vocabulary development by building and analyzing different semantic network models and comparing them to norms based on vocabulary norms for toddlers in this age range. More specifically, the relations between words in our semantic networks were derived from skip-gram neural networks (Word2Vec) trained on our toddler corpus or on Google news. Results revealed that the models built from the toddler corpus were more accurate at predicting toddler vocabulary growth than the adult-based corpus. These results speak to the importance of selecting a corpus that matches the population of interest.
%U https://aclanthology.org/2022.lrec-1.421/
%P 3960-3968
Markdown (Informal)
[Representing the Toddler Lexicon: Do the Corpus and Semantics Matter?](https://aclanthology.org/2022.lrec-1.421/) (Weber & Colunga, LREC 2022)
ACL