@inproceedings{beekhuizen-2025-vorm,
title = "Vorm: Translations and a constrained hypothesis space support unsupervised morphological segmentation across languages",
author = "Beekhuizen, Barend",
editor = "Boleda, Gemma and
Roth, Michael",
booktitle = "Proceedings of the 29th Conference on Computational Natural Language Learning",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.conll-1.39/",
doi = "10.18653/v1/2025.conll-1.39",
pages = "602--626",
ISBN = "979-8-89176-271-8",
abstract = "This paper introduces Vorm, an unsupervised morphological segmentation system, leveraging translation data to infer highly accurate morphological transformations, including less-frequently modeled processes such as infixation and reduplication. The system is evaluated on standard benchmark data and a novel, typologically diverse, dataset of 37 languages. Model performance is competitive and sometimes superior on canonical segmentation, but more limited on surface segmentation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beekhuizen-2025-vorm">
<titleInfo>
<title>Vorm: Translations and a constrained hypothesis space support unsupervised morphological segmentation across languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barend</namePart>
<namePart type="family">Beekhuizen</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>Proceedings of the 29th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gemma</namePart>
<namePart type="family">Boleda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Roth</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">979-8-89176-271-8</identifier>
</relatedItem>
<abstract>This paper introduces Vorm, an unsupervised morphological segmentation system, leveraging translation data to infer highly accurate morphological transformations, including less-frequently modeled processes such as infixation and reduplication. The system is evaluated on standard benchmark data and a novel, typologically diverse, dataset of 37 languages. Model performance is competitive and sometimes superior on canonical segmentation, but more limited on surface segmentation.</abstract>
<identifier type="citekey">beekhuizen-2025-vorm</identifier>
<identifier type="doi">10.18653/v1/2025.conll-1.39</identifier>
<location>
<url>https://aclanthology.org/2025.conll-1.39/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>602</start>
<end>626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vorm: Translations and a constrained hypothesis space support unsupervised morphological segmentation across languages
%A Beekhuizen, Barend
%Y Boleda, Gemma
%Y Roth, Michael
%S Proceedings of the 29th Conference on Computational Natural Language Learning
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-271-8
%F beekhuizen-2025-vorm
%X This paper introduces Vorm, an unsupervised morphological segmentation system, leveraging translation data to infer highly accurate morphological transformations, including less-frequently modeled processes such as infixation and reduplication. The system is evaluated on standard benchmark data and a novel, typologically diverse, dataset of 37 languages. Model performance is competitive and sometimes superior on canonical segmentation, but more limited on surface segmentation.
%R 10.18653/v1/2025.conll-1.39
%U https://aclanthology.org/2025.conll-1.39/
%U https://doi.org/10.18653/v1/2025.conll-1.39
%P 602-626
Markdown (Informal)
[Vorm: Translations and a constrained hypothesis space support unsupervised morphological segmentation across languages](https://aclanthology.org/2025.conll-1.39/) (Beekhuizen, CoNLL 2025)
ACL