@inproceedings{gifford-etal-2026-revisiting,
title = "Revisiting Age of Acquisition in Curriculum Learning: Disentangling Lexical Features and Semantic Structure",
author = "Gifford, Ian and
Shah, Aaron and
Chen, Catherine and
Bachi, Taimaa Kassab and
Portelance, Eva",
editor = "Bonial, Claire and
Berzak, Yevgeni",
booktitle = "Proceedings of the 30th Conference on Computational Natural Language Learning",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.conll-main.40/",
pages = "661--676",
ISBN = "979-8-89176-410-1",
abstract = "Previous work has found that ordering training data by children{'}s Age of Acquisition (AoA) for words increases the stability of distributional word embeddings, suggesting that early-learned words play a privileged role in shaping semantic structure. In this study, we determine whether AoA itself drives these effects, or whether they emerge from correlated lexical factors such as frequency, concreteness, and phonological complexity. Using incremental Word2Vec training, we construct curricula ordered by AoA and by individual lexical features, while systematically controlling for vocabulary growth and deterministic ordering effects. We show that AoA-ordered curricula produce greater early-phase stability than shuffled baselines, even under controlled exposure conditions. We find that the advantage observed with AoA can be largely explained by correlated factors like overall word frequency. Despite limited gains on general similarity benchmarks, AoA-ordered embeddings outperform shuffled embeddings on a proxy domain-specific task: predicting human AoA norms. This advantage persists after debiasing timestamp effects, implying that AoA curricula induce developmentally meaningful semantic structure."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gifford-etal-2026-revisiting">
<titleInfo>
<title>Revisiting Age of Acquisition in Curriculum Learning: Disentangling Lexical Features and Semantic Structure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Gifford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taimaa</namePart>
<namePart type="given">Kassab</namePart>
<namePart type="family">Bachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Portelance</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 30th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yevgeni</namePart>
<namePart type="family">Berzak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-410-1</identifier>
</relatedItem>
<abstract>Previous work has found that ordering training data by children’s Age of Acquisition (AoA) for words increases the stability of distributional word embeddings, suggesting that early-learned words play a privileged role in shaping semantic structure. In this study, we determine whether AoA itself drives these effects, or whether they emerge from correlated lexical factors such as frequency, concreteness, and phonological complexity. Using incremental Word2Vec training, we construct curricula ordered by AoA and by individual lexical features, while systematically controlling for vocabulary growth and deterministic ordering effects. We show that AoA-ordered curricula produce greater early-phase stability than shuffled baselines, even under controlled exposure conditions. We find that the advantage observed with AoA can be largely explained by correlated factors like overall word frequency. Despite limited gains on general similarity benchmarks, AoA-ordered embeddings outperform shuffled embeddings on a proxy domain-specific task: predicting human AoA norms. This advantage persists after debiasing timestamp effects, implying that AoA curricula induce developmentally meaningful semantic structure.</abstract>
<identifier type="citekey">gifford-etal-2026-revisiting</identifier>
<location>
<url>https://aclanthology.org/2026.conll-main.40/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>661</start>
<end>676</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Age of Acquisition in Curriculum Learning: Disentangling Lexical Features and Semantic Structure
%A Gifford, Ian
%A Shah, Aaron
%A Chen, Catherine
%A Bachi, Taimaa Kassab
%A Portelance, Eva
%Y Bonial, Claire
%Y Berzak, Yevgeni
%S Proceedings of the 30th Conference on Computational Natural Language Learning
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-410-1
%F gifford-etal-2026-revisiting
%X Previous work has found that ordering training data by children’s Age of Acquisition (AoA) for words increases the stability of distributional word embeddings, suggesting that early-learned words play a privileged role in shaping semantic structure. In this study, we determine whether AoA itself drives these effects, or whether they emerge from correlated lexical factors such as frequency, concreteness, and phonological complexity. Using incremental Word2Vec training, we construct curricula ordered by AoA and by individual lexical features, while systematically controlling for vocabulary growth and deterministic ordering effects. We show that AoA-ordered curricula produce greater early-phase stability than shuffled baselines, even under controlled exposure conditions. We find that the advantage observed with AoA can be largely explained by correlated factors like overall word frequency. Despite limited gains on general similarity benchmarks, AoA-ordered embeddings outperform shuffled embeddings on a proxy domain-specific task: predicting human AoA norms. This advantage persists after debiasing timestamp effects, implying that AoA curricula induce developmentally meaningful semantic structure.
%U https://aclanthology.org/2026.conll-main.40/
%P 661-676
Markdown (Informal)
[Revisiting Age of Acquisition in Curriculum Learning: Disentangling Lexical Features and Semantic Structure](https://aclanthology.org/2026.conll-main.40/) (Gifford et al., CoNLL 2026)
ACL