@inproceedings{behrooznia-etal-2024-enhancing,
title = "Enhancing {T}urkish Word Segmentation: A Focus on Borrowed Words and Invalid Morpheme",
author = "Behrooznia, Soheila and
Ansari, Ebrahim and
Zabokrtsky, Zdenek",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.loresmt-1.9",
doi = "10.18653/v1/2024.loresmt-1.9",
pages = "85--93",
abstract = "This study addresses a challenge in morphological segmentation: accurately segmenting words in languages with rich morphology. Current probabilistic methods, such as Morfessor, often produce results that lack consistency with human-segmented words. Our study adds some steps to the Morfessor segmentation process to consider invalid morphemes and borrowed words from other languages to improve morphological segmentation significantly. Comparing our idea to the results obtained from Morfessor demonstrates its efficiency, leading to more accurate morphology segmentation. This is particularly evident in the case of Turkish, highlighting the potential for further advancements in morpheme segmentation for morphologically rich languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="behrooznia-etal-2024-enhancing">
<titleInfo>
<title>Enhancing Turkish Word Segmentation: A Focus on Borrowed Words and Invalid Morpheme</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soheila</namePart>
<namePart type="family">Behrooznia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ebrahim</namePart>
<namePart type="family">Ansari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdenek</namePart>
<namePart type="family">Zabokrtsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study addresses a challenge in morphological segmentation: accurately segmenting words in languages with rich morphology. Current probabilistic methods, such as Morfessor, often produce results that lack consistency with human-segmented words. Our study adds some steps to the Morfessor segmentation process to consider invalid morphemes and borrowed words from other languages to improve morphological segmentation significantly. Comparing our idea to the results obtained from Morfessor demonstrates its efficiency, leading to more accurate morphology segmentation. This is particularly evident in the case of Turkish, highlighting the potential for further advancements in morpheme segmentation for morphologically rich languages.</abstract>
<identifier type="citekey">behrooznia-etal-2024-enhancing</identifier>
<identifier type="doi">10.18653/v1/2024.loresmt-1.9</identifier>
<location>
<url>https://aclanthology.org/2024.loresmt-1.9</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>85</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Turkish Word Segmentation: A Focus on Borrowed Words and Invalid Morpheme
%A Behrooznia, Soheila
%A Ansari, Ebrahim
%A Zabokrtsky, Zdenek
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F behrooznia-etal-2024-enhancing
%X This study addresses a challenge in morphological segmentation: accurately segmenting words in languages with rich morphology. Current probabilistic methods, such as Morfessor, often produce results that lack consistency with human-segmented words. Our study adds some steps to the Morfessor segmentation process to consider invalid morphemes and borrowed words from other languages to improve morphological segmentation significantly. Comparing our idea to the results obtained from Morfessor demonstrates its efficiency, leading to more accurate morphology segmentation. This is particularly evident in the case of Turkish, highlighting the potential for further advancements in morpheme segmentation for morphologically rich languages.
%R 10.18653/v1/2024.loresmt-1.9
%U https://aclanthology.org/2024.loresmt-1.9
%U https://doi.org/10.18653/v1/2024.loresmt-1.9
%P 85-93
Markdown (Informal)
[Enhancing Turkish Word Segmentation: A Focus on Borrowed Words and Invalid Morpheme](https://aclanthology.org/2024.loresmt-1.9) (Behrooznia et al., LoResMT-WS 2024)
ACL