@inproceedings{haga-etal-2024-modeling,
title = "Modeling Overregularization in Children with Small Language Models",
author = "Haga, Akari and
Sugawara, Saku and
Fukatsu, Akiyo and
Oba, Miyu and
Ouchi, Hiroki and
Watanabe, Taro and
Oseki, Yohei",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.865",
pages = "14532--14550",
abstract = "The imitation of the children{'}s language acquisition process has been explored to make language models (LMs) more efficient.In particular, errors caused by children{'}s regularization (so-called overregularization, e.g., using wroted for the past tense of write) have been widely studied to reveal the mechanisms of language acquisition. Existing research has analyzed regularization in language acquisition only by modeling word inflection directly, which is unnatural in light of human language acquisition. In this paper, we hypothesize that language models that imitate the errors children make during language acquisition have a learning process more similar to humans. To verify this hypothesis, we analyzed the learning curve and error preferences of verb inflections in small-scale LMs using acceptability judgments. We analyze the differences in results by model architecture, data, and tokenization. Our model shows child-like U-shaped learning curves clearly for certain verbs, but the preferences for types of overgeneralization did not fully match the observations in children.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haga-etal-2024-modeling">
<titleInfo>
<title>Modeling Overregularization in Children with Small Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Haga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saku</namePart>
<namePart type="family">Sugawara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiyo</namePart>
<namePart type="family">Fukatsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miyu</namePart>
<namePart type="family">Oba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Oseki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The imitation of the children’s language acquisition process has been explored to make language models (LMs) more efficient.In particular, errors caused by children’s regularization (so-called overregularization, e.g., using wroted for the past tense of write) have been widely studied to reveal the mechanisms of language acquisition. Existing research has analyzed regularization in language acquisition only by modeling word inflection directly, which is unnatural in light of human language acquisition. In this paper, we hypothesize that language models that imitate the errors children make during language acquisition have a learning process more similar to humans. To verify this hypothesis, we analyzed the learning curve and error preferences of verb inflections in small-scale LMs using acceptability judgments. We analyze the differences in results by model architecture, data, and tokenization. Our model shows child-like U-shaped learning curves clearly for certain verbs, but the preferences for types of overgeneralization did not fully match the observations in children.</abstract>
<identifier type="citekey">haga-etal-2024-modeling</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.865</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14532</start>
<end>14550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Overregularization in Children with Small Language Models
%A Haga, Akari
%A Sugawara, Saku
%A Fukatsu, Akiyo
%A Oba, Miyu
%A Ouchi, Hiroki
%A Watanabe, Taro
%A Oseki, Yohei
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F haga-etal-2024-modeling
%X The imitation of the children’s language acquisition process has been explored to make language models (LMs) more efficient.In particular, errors caused by children’s regularization (so-called overregularization, e.g., using wroted for the past tense of write) have been widely studied to reveal the mechanisms of language acquisition. Existing research has analyzed regularization in language acquisition only by modeling word inflection directly, which is unnatural in light of human language acquisition. In this paper, we hypothesize that language models that imitate the errors children make during language acquisition have a learning process more similar to humans. To verify this hypothesis, we analyzed the learning curve and error preferences of verb inflections in small-scale LMs using acceptability judgments. We analyze the differences in results by model architecture, data, and tokenization. Our model shows child-like U-shaped learning curves clearly for certain verbs, but the preferences for types of overgeneralization did not fully match the observations in children.
%U https://aclanthology.org/2024.findings-acl.865
%P 14532-14550
Markdown (Informal)
[Modeling Overregularization in Children with Small Language Models](https://aclanthology.org/2024.findings-acl.865) (Haga et al., Findings 2024)
ACL
- Akari Haga, Saku Sugawara, Akiyo Fukatsu, Miyu Oba, Hiroki Ouchi, Taro Watanabe, and Yohei Oseki. 2024. Modeling Overregularization in Children with Small Language Models. In Findings of the Association for Computational Linguistics ACL 2024, pages 14532–14550, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.