@inproceedings{pranjic-etal-2024-llmsegm,
title = "{LLMS}egm: Surface-level Morphological Segmentation Using Large Language Model",
author = "Pranji{\'c}, Marko and
Robnik-{\v{S}}ikonja, Marko and
Pollak, Senja",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.933",
pages = "10665--10674",
abstract = "Morphological word segmentation splits a given word into its morphemes (roots and affixes), the smallest meaning-bearing units of language. We introduce a novel approach, called LLMSegm, to surface-level morphological segmentation leveraging large language models (LLMs). The proposed approach is applicable in low-data settings as well as for low-resourced languages. We show how to transform the surface-level morphological segmentation task to a binary classification problem and train LLMs to solve it efficiently. For input, we leverage the information from the default LLM subword tokenisation, and a custom morphological segmentation using novel encoding. The evaluation of LLMSegm across seven morphologically diverse languages demonstrates substantial gains in minimally-supervised settings as well as for low-resourced languages, compared to several existing competitive approaches. In terms of F1-scores and accuracy, we achieve improved results compared to the competing methods in six out of seven datasets. Keywords: morphological segmentation, surface-level segmentation, large language models, low-resource settings",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pranjic-etal-2024-llmsegm">
<titleInfo>
<title>LLMSegm: Surface-level Morphological Segmentation Using Large Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Pranjić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Robnik-Šikonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Morphological word segmentation splits a given word into its morphemes (roots and affixes), the smallest meaning-bearing units of language. We introduce a novel approach, called LLMSegm, to surface-level morphological segmentation leveraging large language models (LLMs). The proposed approach is applicable in low-data settings as well as for low-resourced languages. We show how to transform the surface-level morphological segmentation task to a binary classification problem and train LLMs to solve it efficiently. For input, we leverage the information from the default LLM subword tokenisation, and a custom morphological segmentation using novel encoding. The evaluation of LLMSegm across seven morphologically diverse languages demonstrates substantial gains in minimally-supervised settings as well as for low-resourced languages, compared to several existing competitive approaches. In terms of F1-scores and accuracy, we achieve improved results compared to the competing methods in six out of seven datasets. Keywords: morphological segmentation, surface-level segmentation, large language models, low-resource settings</abstract>
<identifier type="citekey">pranjic-etal-2024-llmsegm</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.933</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10665</start>
<end>10674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMSegm: Surface-level Morphological Segmentation Using Large Language Model
%A Pranjić, Marko
%A Robnik-Šikonja, Marko
%A Pollak, Senja
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F pranjic-etal-2024-llmsegm
%X Morphological word segmentation splits a given word into its morphemes (roots and affixes), the smallest meaning-bearing units of language. We introduce a novel approach, called LLMSegm, to surface-level morphological segmentation leveraging large language models (LLMs). The proposed approach is applicable in low-data settings as well as for low-resourced languages. We show how to transform the surface-level morphological segmentation task to a binary classification problem and train LLMs to solve it efficiently. For input, we leverage the information from the default LLM subword tokenisation, and a custom morphological segmentation using novel encoding. The evaluation of LLMSegm across seven morphologically diverse languages demonstrates substantial gains in minimally-supervised settings as well as for low-resourced languages, compared to several existing competitive approaches. In terms of F1-scores and accuracy, we achieve improved results compared to the competing methods in six out of seven datasets. Keywords: morphological segmentation, surface-level segmentation, large language models, low-resource settings
%U https://aclanthology.org/2024.lrec-main.933
%P 10665-10674
Markdown (Informal)
[LLMSegm: Surface-level Morphological Segmentation Using Large Language Model](https://aclanthology.org/2024.lrec-main.933) (Pranjić et al., LREC-COLING 2024)
ACL