@inproceedings{astrach-pinter-2025-probing,
title = "Probing Subphonemes in Morphology Models",
author = "Astrach, Gal and
Pinter, Yuval",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.672/",
doi = "10.18653/v1/2025.findings-acl.672",
pages = "12954--12961",
ISBN = "979-8-89176-256-5",
abstract = "Transformers have achieved state-of-the-art performance in morphological inflection tasks, yet their ability to generalize across languages and morphological rules remains limited. One possible explanation for this behavior can be the degree to which these models are able to capture implicit phenomena at the phonological and subphonemic levels. We introduce a language-agnostic probing method to investigate phonological feature encoding in transformers trained directly on phonemes, and perform it across seven morphologically diverse languages. We show that phonological features which are local, such as final-obstruent devoicing in Turkish, are captured well in phoneme embeddings, whereas long-distance dependencies like vowel harmony are better represented in the transformer{'}s encoder. Finally, we discuss how these findings inform empirical strategies for training morphological models, particularly regarding the role of subphonemic feature acquisition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="astrach-pinter-2025-probing">
<titleInfo>
<title>Probing Subphonemes in Morphology Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gal</namePart>
<namePart type="family">Astrach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Transformers have achieved state-of-the-art performance in morphological inflection tasks, yet their ability to generalize across languages and morphological rules remains limited. One possible explanation for this behavior can be the degree to which these models are able to capture implicit phenomena at the phonological and subphonemic levels. We introduce a language-agnostic probing method to investigate phonological feature encoding in transformers trained directly on phonemes, and perform it across seven morphologically diverse languages. We show that phonological features which are local, such as final-obstruent devoicing in Turkish, are captured well in phoneme embeddings, whereas long-distance dependencies like vowel harmony are better represented in the transformer’s encoder. Finally, we discuss how these findings inform empirical strategies for training morphological models, particularly regarding the role of subphonemic feature acquisition.</abstract>
<identifier type="citekey">astrach-pinter-2025-probing</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.672</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.672/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>12954</start>
<end>12961</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing Subphonemes in Morphology Models
%A Astrach, Gal
%A Pinter, Yuval
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F astrach-pinter-2025-probing
%X Transformers have achieved state-of-the-art performance in morphological inflection tasks, yet their ability to generalize across languages and morphological rules remains limited. One possible explanation for this behavior can be the degree to which these models are able to capture implicit phenomena at the phonological and subphonemic levels. We introduce a language-agnostic probing method to investigate phonological feature encoding in transformers trained directly on phonemes, and perform it across seven morphologically diverse languages. We show that phonological features which are local, such as final-obstruent devoicing in Turkish, are captured well in phoneme embeddings, whereas long-distance dependencies like vowel harmony are better represented in the transformer’s encoder. Finally, we discuss how these findings inform empirical strategies for training morphological models, particularly regarding the role of subphonemic feature acquisition.
%R 10.18653/v1/2025.findings-acl.672
%U https://aclanthology.org/2025.findings-acl.672/
%U https://doi.org/10.18653/v1/2025.findings-acl.672
%P 12954-12961
Markdown (Informal)
[Probing Subphonemes in Morphology Models](https://aclanthology.org/2025.findings-acl.672/) (Astrach & Pinter, Findings 2025)
ACL
- Gal Astrach and Yuval Pinter. 2025. Probing Subphonemes in Morphology Models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 12954–12961, Vienna, Austria. Association for Computational Linguistics.