@inproceedings{xu-giulianelli-2026-much,
title = "How Much Sonority Structure Do Phonotactic Language Models Learn from Distribution?",
author = "Xu, Jia Can and
Giulianelli, Mario",
editor = "Arad, Dana and
Belinkov, Yonatan and
Chen, Hanjie and
Feldhus, Nils and
Mueller, Aaron and
Mohebbi, Hosein and
Sarti, Gabriele and
Tutek, Martin",
booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.blackboxnlp-1.44/",
pages = "761--782",
ISBN = "979-8-89176-476-7",
abstract = "Sonority projection, the ability to rank unattested consonant clusters by their sonority contour, has been interpreted as evidence for innate phonological knowledge. We test whether neural phonotactic language models can acquire sonority structure from English phoneme distributions through a controlled comparison of four input geometries: articulatory features, trainable embeddings, feature vectors randomly reassigned to phonemes, and frozen random vectors. We train LSTMs and Transformers, probe whether sonority structure is linearly recoverable across representation spaces and throughout training, and evaluate phonotactic sensitivity using nonce-word violations and human acceptability judgements of unattested onsets. Sonority probes recover the consonant{--}vowel distinction from contextual phoneme representations under every input condition, whereas the hierarchy among consonant classes (obstruents, nasals, liquids, and glides) is most strongly recoverable with articulatory-feature input and less recoverable under the other conditions. Nevertheless, under all input geometry conditions, model surprisal discriminates phonotactic violations and correlates moderately with human judgements of unattested onsets. In summary, sonority structure and the tested phonotactic preferences can develop without sonority-aligned input representations: input geometry shapes how much fine-grained sonority structure is recoverable, but models with more recoverable structure, whether provided explicitly or learned during training, at the input or in the hidden states, show no consistent advantage on the phonotactic evaluations used here."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-giulianelli-2026-much">
<titleInfo>
<title>How Much Sonority Structure Do Phonotactic Language Models Learn from Distribution?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="given">Can</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Giulianelli</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>Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tutek</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">979-8-89176-476-7</identifier>
</relatedItem>
<abstract>Sonority projection, the ability to rank unattested consonant clusters by their sonority contour, has been interpreted as evidence for innate phonological knowledge. We test whether neural phonotactic language models can acquire sonority structure from English phoneme distributions through a controlled comparison of four input geometries: articulatory features, trainable embeddings, feature vectors randomly reassigned to phonemes, and frozen random vectors. We train LSTMs and Transformers, probe whether sonority structure is linearly recoverable across representation spaces and throughout training, and evaluate phonotactic sensitivity using nonce-word violations and human acceptability judgements of unattested onsets. Sonority probes recover the consonant–vowel distinction from contextual phoneme representations under every input condition, whereas the hierarchy among consonant classes (obstruents, nasals, liquids, and glides) is most strongly recoverable with articulatory-feature input and less recoverable under the other conditions. Nevertheless, under all input geometry conditions, model surprisal discriminates phonotactic violations and correlates moderately with human judgements of unattested onsets. In summary, sonority structure and the tested phonotactic preferences can develop without sonority-aligned input representations: input geometry shapes how much fine-grained sonority structure is recoverable, but models with more recoverable structure, whether provided explicitly or learned during training, at the input or in the hidden states, show no consistent advantage on the phonotactic evaluations used here.</abstract>
<identifier type="citekey">xu-giulianelli-2026-much</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.44/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>761</start>
<end>782</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Much Sonority Structure Do Phonotactic Language Models Learn from Distribution?
%A Xu, Jia Can
%A Giulianelli, Mario
%Y Arad, Dana
%Y Belinkov, Yonatan
%Y Chen, Hanjie
%Y Feldhus, Nils
%Y Mueller, Aaron
%Y Mohebbi, Hosein
%Y Sarti, Gabriele
%Y Tutek, Martin
%S Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-476-7
%F xu-giulianelli-2026-much
%X Sonority projection, the ability to rank unattested consonant clusters by their sonority contour, has been interpreted as evidence for innate phonological knowledge. We test whether neural phonotactic language models can acquire sonority structure from English phoneme distributions through a controlled comparison of four input geometries: articulatory features, trainable embeddings, feature vectors randomly reassigned to phonemes, and frozen random vectors. We train LSTMs and Transformers, probe whether sonority structure is linearly recoverable across representation spaces and throughout training, and evaluate phonotactic sensitivity using nonce-word violations and human acceptability judgements of unattested onsets. Sonority probes recover the consonant–vowel distinction from contextual phoneme representations under every input condition, whereas the hierarchy among consonant classes (obstruents, nasals, liquids, and glides) is most strongly recoverable with articulatory-feature input and less recoverable under the other conditions. Nevertheless, under all input geometry conditions, model surprisal discriminates phonotactic violations and correlates moderately with human judgements of unattested onsets. In summary, sonority structure and the tested phonotactic preferences can develop without sonority-aligned input representations: input geometry shapes how much fine-grained sonority structure is recoverable, but models with more recoverable structure, whether provided explicitly or learned during training, at the input or in the hidden states, show no consistent advantage on the phonotactic evaluations used here.
%U https://aclanthology.org/2026.blackboxnlp-1.44/
%P 761-782
Markdown (Informal)
[How Much Sonority Structure Do Phonotactic Language Models Learn from Distribution?](https://aclanthology.org/2026.blackboxnlp-1.44/) (Xu & Giulianelli, BlackboxNLP 2026)
ACL