@inproceedings{gidey-etal-2024-morphological,
title = "Morphological Synthesizer for {G}e{'}ez Language: Addressing Morphological Complexity and Resource Limitations",
author = "Gidey, Gebrearegawi Gebremariam and
Teklehaymanot, Hailay Kidu and
Atsbha, Gebregewergs Mezgebe",
editor = "Mabuya, Rooweither and
Matfunjwa, Muzi and
Setaka, Mmasibidi and
van Zaanen, Menno",
booktitle = "Proceedings of the Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.rail-1.11",
pages = "94--106",
abstract = "Ge{'}ez is an ancient Semitic language renowned for its unique alphabet. It serves as the script for numerous lan- guages, including Tigrinya and Amharic, and played a pivotal role in Ethiopia{'}s cultural and religious development during the Aksumite kingdom era. Ge{'}ez remains significant as a liturgical language in Ethiopia and Eritrea, with much of the national identity documentation recorded in Ge{'}ez. These written materials are invaluable primary sources for studying Ethiopian and Eritrean philosophy, creativity, knowledge, and civilization. Ge{'}ez is a complex morphological structure with rich inflectional and derivational morphology, and no usable NLP has been developed and published until now due to the scarcity of annotated linguistic data, corpora, labeled datasets, and lexicons. Therefore, we proposed a rule-based Ge{'}ez morphological synthesis to generate surface words from root words according to the morphological structures of the language. Consequently, we proposed an automatic morphological synthesizer for Ge{'}ez using TLM. We used 1,102 sample verbs, representing all verb morphological structures, to test and evaluate the system. Finally, we get a performance of 97.4{\%}. This result outperforms the baseline model, suggesting that other scholars build a comprehensive system considering morphological variations of the language. Keywords: Ge{'}ez, NLP, morphology, morphological synthesizer, rule-based",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gidey-etal-2024-morphological">
<titleInfo>
<title>Morphological Synthesizer for Ge’ez Language: Addressing Morphological Complexity and Resource Limitations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gebrearegawi</namePart>
<namePart type="given">Gebremariam</namePart>
<namePart type="family">Gidey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailay</namePart>
<namePart type="given">Kidu</namePart>
<namePart type="family">Teklehaymanot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gebregewergs</namePart>
<namePart type="given">Mezgebe</namePart>
<namePart type="family">Atsbha</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 Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muzi</namePart>
<namePart type="family">Matfunjwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</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>Ge’ez is an ancient Semitic language renowned for its unique alphabet. It serves as the script for numerous lan- guages, including Tigrinya and Amharic, and played a pivotal role in Ethiopia’s cultural and religious development during the Aksumite kingdom era. Ge’ez remains significant as a liturgical language in Ethiopia and Eritrea, with much of the national identity documentation recorded in Ge’ez. These written materials are invaluable primary sources for studying Ethiopian and Eritrean philosophy, creativity, knowledge, and civilization. Ge’ez is a complex morphological structure with rich inflectional and derivational morphology, and no usable NLP has been developed and published until now due to the scarcity of annotated linguistic data, corpora, labeled datasets, and lexicons. Therefore, we proposed a rule-based Ge’ez morphological synthesis to generate surface words from root words according to the morphological structures of the language. Consequently, we proposed an automatic morphological synthesizer for Ge’ez using TLM. We used 1,102 sample verbs, representing all verb morphological structures, to test and evaluate the system. Finally, we get a performance of 97.4%. This result outperforms the baseline model, suggesting that other scholars build a comprehensive system considering morphological variations of the language. Keywords: Ge’ez, NLP, morphology, morphological synthesizer, rule-based</abstract>
<identifier type="citekey">gidey-etal-2024-morphological</identifier>
<location>
<url>https://aclanthology.org/2024.rail-1.11</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>94</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphological Synthesizer for Ge’ez Language: Addressing Morphological Complexity and Resource Limitations
%A Gidey, Gebrearegawi Gebremariam
%A Teklehaymanot, Hailay Kidu
%A Atsbha, Gebregewergs Mezgebe
%Y Mabuya, Rooweither
%Y Matfunjwa, Muzi
%Y Setaka, Mmasibidi
%Y van Zaanen, Menno
%S Proceedings of the Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F gidey-etal-2024-morphological
%X Ge’ez is an ancient Semitic language renowned for its unique alphabet. It serves as the script for numerous lan- guages, including Tigrinya and Amharic, and played a pivotal role in Ethiopia’s cultural and religious development during the Aksumite kingdom era. Ge’ez remains significant as a liturgical language in Ethiopia and Eritrea, with much of the national identity documentation recorded in Ge’ez. These written materials are invaluable primary sources for studying Ethiopian and Eritrean philosophy, creativity, knowledge, and civilization. Ge’ez is a complex morphological structure with rich inflectional and derivational morphology, and no usable NLP has been developed and published until now due to the scarcity of annotated linguistic data, corpora, labeled datasets, and lexicons. Therefore, we proposed a rule-based Ge’ez morphological synthesis to generate surface words from root words according to the morphological structures of the language. Consequently, we proposed an automatic morphological synthesizer for Ge’ez using TLM. We used 1,102 sample verbs, representing all verb morphological structures, to test and evaluate the system. Finally, we get a performance of 97.4%. This result outperforms the baseline model, suggesting that other scholars build a comprehensive system considering morphological variations of the language. Keywords: Ge’ez, NLP, morphology, morphological synthesizer, rule-based
%U https://aclanthology.org/2024.rail-1.11
%P 94-106
Markdown (Informal)
[Morphological Synthesizer for Ge’ez Language: Addressing Morphological Complexity and Resource Limitations](https://aclanthology.org/2024.rail-1.11) (Gidey et al., RAIL-WS 2024)
ACL