@inproceedings{yang-etal-2026-phonological,
title = "Phonological Abstraction and Exception Memorization in Noisy Tone Learning",
author = "Yang, Yi and
Wang, Yiming and
Yuan, Jiahong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1693/",
pages = "36181--36199",
ISBN = "979-8-89176-462-0",
abstract = "Transformer-based speech models have recently been shown to perform well under impoverished and ambiguous supervision, a setting motivated by poverty-of-the-stimulus arguments, yet their learning dynamics remain unclear. In this work, we study this question with wav2vec2.0 on Mandarin tone classification, using 70 scale{--}noise configurations, capacity interventions, and perturbation probes to examine the dynamics of abstraction-consistent generalization and exception memorization, yielding representative regimes of Robust Generalization, Abrupt Transition, and High-noise Collapse. We find a consistent abstraction{--}exception trajectory: when phonological recovery is possible, the model first exhibits phonologically abstraction-consistent behavior and only later fits corrupted labels as empirical exceptions. Capacity analyses show that this trajectory is not merely a large-model artifact: it persists under truncated Transformer encoders, while acoustic rank compression modulates but does not selectively separate abstraction from exception memorization. Finally, acoustic perturbations show different local robustness: abstraction-consistent predictions remain stable under stronger waveform perturbations, whereas fitted exceptions behave as fragile local overrides on top of the broader abstraction-consistent behavior."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-phonological">
<titleInfo>
<title>Phonological Abstraction and Exception Memorization in Noisy Tone Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahong</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Transformer-based speech models have recently been shown to perform well under impoverished and ambiguous supervision, a setting motivated by poverty-of-the-stimulus arguments, yet their learning dynamics remain unclear. In this work, we study this question with wav2vec2.0 on Mandarin tone classification, using 70 scale–noise configurations, capacity interventions, and perturbation probes to examine the dynamics of abstraction-consistent generalization and exception memorization, yielding representative regimes of Robust Generalization, Abrupt Transition, and High-noise Collapse. We find a consistent abstraction–exception trajectory: when phonological recovery is possible, the model first exhibits phonologically abstraction-consistent behavior and only later fits corrupted labels as empirical exceptions. Capacity analyses show that this trajectory is not merely a large-model artifact: it persists under truncated Transformer encoders, while acoustic rank compression modulates but does not selectively separate abstraction from exception memorization. Finally, acoustic perturbations show different local robustness: abstraction-consistent predictions remain stable under stronger waveform perturbations, whereas fitted exceptions behave as fragile local overrides on top of the broader abstraction-consistent behavior.</abstract>
<identifier type="citekey">yang-etal-2026-phonological</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1693/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>36181</start>
<end>36199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phonological Abstraction and Exception Memorization in Noisy Tone Learning
%A Yang, Yi
%A Wang, Yiming
%A Yuan, Jiahong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F yang-etal-2026-phonological
%X Transformer-based speech models have recently been shown to perform well under impoverished and ambiguous supervision, a setting motivated by poverty-of-the-stimulus arguments, yet their learning dynamics remain unclear. In this work, we study this question with wav2vec2.0 on Mandarin tone classification, using 70 scale–noise configurations, capacity interventions, and perturbation probes to examine the dynamics of abstraction-consistent generalization and exception memorization, yielding representative regimes of Robust Generalization, Abrupt Transition, and High-noise Collapse. We find a consistent abstraction–exception trajectory: when phonological recovery is possible, the model first exhibits phonologically abstraction-consistent behavior and only later fits corrupted labels as empirical exceptions. Capacity analyses show that this trajectory is not merely a large-model artifact: it persists under truncated Transformer encoders, while acoustic rank compression modulates but does not selectively separate abstraction from exception memorization. Finally, acoustic perturbations show different local robustness: abstraction-consistent predictions remain stable under stronger waveform perturbations, whereas fitted exceptions behave as fragile local overrides on top of the broader abstraction-consistent behavior.
%U https://aclanthology.org/2026.findings-emnlp.1693/
%P 36181-36199
Markdown (Informal)
[Phonological Abstraction and Exception Memorization in Noisy Tone Learning](https://aclanthology.org/2026.findings-emnlp.1693/) (Yang et al., Findings 2026)
ACL