@inproceedings{salehi-jacobs-2024-effect,
title = "The Effect of Model Capacity and Script Diversity on Subword Tokenization for {S}orani {K}urdish",
author = "Salehi, Ali and
Jacobs, Cassandra L.",
editor = {Nicolai, Garrett and
Chodroff, Eleanor and
Mailhot, Frederic and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
booktitle = "Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigmorphon-1.6",
doi = "10.18653/v1/2024.sigmorphon-1.6",
pages = "51--56",
abstract = "Tokenization and morphological segmentation continue to pose challenges for text processing and studies of human language. Here, we focus on written Soran{\^\i} Kurdish, which uses a modified script based on Persian and Arabic, and its transliterations into the Kurdish Latin script. Importantly, Perso-Arabic and Latin-based writing systems demonstrate different statistical and structural properties, which may have significant effects on subword vocabulary learning. This has major consequences for frequency- or probability-based models of morphological induction. We explore the possibility that jointly training subword vocabularies using a source script along with its transliteration would improve morphological segmentation, subword tokenization, and whether gains are observed for one system over others. We find that joint training has a similar effect to increasing vocabulary size, while keeping subwords shorter in length, which produces higher-quality subwords that map onto morphemes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salehi-jacobs-2024-effect">
<titleInfo>
<title>The Effect of Model Capacity and Script Diversity on Subword Tokenization for Sorani Kurdish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Salehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassandra</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Jacobs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleanor</namePart>
<namePart type="family">Chodroff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Mailhot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Tokenization and morphological segmentation continue to pose challenges for text processing and studies of human language. Here, we focus on written Soranî Kurdish, which uses a modified script based on Persian and Arabic, and its transliterations into the Kurdish Latin script. Importantly, Perso-Arabic and Latin-based writing systems demonstrate different statistical and structural properties, which may have significant effects on subword vocabulary learning. This has major consequences for frequency- or probability-based models of morphological induction. We explore the possibility that jointly training subword vocabularies using a source script along with its transliteration would improve morphological segmentation, subword tokenization, and whether gains are observed for one system over others. We find that joint training has a similar effect to increasing vocabulary size, while keeping subwords shorter in length, which produces higher-quality subwords that map onto morphemes.</abstract>
<identifier type="citekey">salehi-jacobs-2024-effect</identifier>
<identifier type="doi">10.18653/v1/2024.sigmorphon-1.6</identifier>
<location>
<url>https://aclanthology.org/2024.sigmorphon-1.6</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>51</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Effect of Model Capacity and Script Diversity on Subword Tokenization for Sorani Kurdish
%A Salehi, Ali
%A Jacobs, Cassandra L.
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%Y Mailhot, Frederic
%Y Çöltekin, Çağrı
%S Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F salehi-jacobs-2024-effect
%X Tokenization and morphological segmentation continue to pose challenges for text processing and studies of human language. Here, we focus on written Soranî Kurdish, which uses a modified script based on Persian and Arabic, and its transliterations into the Kurdish Latin script. Importantly, Perso-Arabic and Latin-based writing systems demonstrate different statistical and structural properties, which may have significant effects on subword vocabulary learning. This has major consequences for frequency- or probability-based models of morphological induction. We explore the possibility that jointly training subword vocabularies using a source script along with its transliteration would improve morphological segmentation, subword tokenization, and whether gains are observed for one system over others. We find that joint training has a similar effect to increasing vocabulary size, while keeping subwords shorter in length, which produces higher-quality subwords that map onto morphemes.
%R 10.18653/v1/2024.sigmorphon-1.6
%U https://aclanthology.org/2024.sigmorphon-1.6
%U https://doi.org/10.18653/v1/2024.sigmorphon-1.6
%P 51-56
Markdown (Informal)
[The Effect of Model Capacity and Script Diversity on Subword Tokenization for Sorani Kurdish](https://aclanthology.org/2024.sigmorphon-1.6) (Salehi & Jacobs, SIGMORPHON 2024)
ACL