@inproceedings{alemayehu-etal-2026-amharic,
title = "{A}mharic {DB}pedia Chapter: A Knowledge Graph for a Low-Resource Language",
author = "Alemayehu, HIzkiel Mitiku and
Taffa, Tilahun Abedissa and
Bayissa, Meti Adane and
Zewge, Andargachew Asfaw and
Zahera, Hamada and
Usbeck, Ricardo and
Ngonga Ngomo, Axel-Cyrille",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.627/",
doi = "10.63317/536jn6g8rjnx",
pages = "7894--7904",
abstract = "DBpedia is a community-driven project that extracts structured knowledge from Wikipedia via language-specific chapters. We present the first steps toward the Amharic DBpedia chapter by extending the DBpedia Extraction Framework (DEF) to support Amharic Wikipedia, including language-specific components such as Ethiopian date parsers, an Ethiopian{--}Gregorian calendar converter, an Arabic{--}Ge{'}ez number converter, and Amharic template mappings, together with automated extraction pipelines and the publication of the resulting knowledge graph through a live website, DBpedia Databus collection, and query endpoints. For mapping, we evaluate the zero-shot NLLB-200 translation model on Amharic infobox property names, achieving a BLEU score of 45.31. For ontology alignment, we link mapped properties to DBpedia ontology properties across 58 DBpedia classes and benchmark multilingual encoders with Amharic support, including Afro-XLM-R Base, XLM-R Base, and Amharic fine-tuned mBERT. The fine-tuned Afro-XLM-R model achieves 92.1{\%} Top-10 accuracy and strong ranking performance, as measured by Mean Reciprocal Rank (MRR). We release all resources developed for the Amharic DBpedia chapter, including the Ethiopian date parser, Ethiopian{--}Gregorian calendar converter, Arabic{--}Geʽez numeral converter, Amharic template mappings, automated extraction workflows, and the resulting Amharic DBpedia knowledge graph with public access via the DBpedia Databus collection, Tentris query endpoint, and the live website at am.dbpedia.org."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alemayehu-etal-2026-amharic">
<titleInfo>
<title>Amharic DBpedia Chapter: A Knowledge Graph for a Low-Resource Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">HIzkiel</namePart>
<namePart type="given">Mitiku</namePart>
<namePart type="family">Alemayehu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tilahun</namePart>
<namePart type="given">Abedissa</namePart>
<namePart type="family">Taffa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meti</namePart>
<namePart type="given">Adane</namePart>
<namePart type="family">Bayissa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andargachew</namePart>
<namePart type="given">Asfaw</namePart>
<namePart type="family">Zewge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamada</namePart>
<namePart type="family">Zahera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Usbeck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel-Cyrille</namePart>
<namePart type="family">Ngonga Ngomo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>DBpedia is a community-driven project that extracts structured knowledge from Wikipedia via language-specific chapters. We present the first steps toward the Amharic DBpedia chapter by extending the DBpedia Extraction Framework (DEF) to support Amharic Wikipedia, including language-specific components such as Ethiopian date parsers, an Ethiopian–Gregorian calendar converter, an Arabic–Ge’ez number converter, and Amharic template mappings, together with automated extraction pipelines and the publication of the resulting knowledge graph through a live website, DBpedia Databus collection, and query endpoints. For mapping, we evaluate the zero-shot NLLB-200 translation model on Amharic infobox property names, achieving a BLEU score of 45.31. For ontology alignment, we link mapped properties to DBpedia ontology properties across 58 DBpedia classes and benchmark multilingual encoders with Amharic support, including Afro-XLM-R Base, XLM-R Base, and Amharic fine-tuned mBERT. The fine-tuned Afro-XLM-R model achieves 92.1% Top-10 accuracy and strong ranking performance, as measured by Mean Reciprocal Rank (MRR). We release all resources developed for the Amharic DBpedia chapter, including the Ethiopian date parser, Ethiopian–Gregorian calendar converter, Arabic–Geʽez numeral converter, Amharic template mappings, automated extraction workflows, and the resulting Amharic DBpedia knowledge graph with public access via the DBpedia Databus collection, Tentris query endpoint, and the live website at am.dbpedia.org.</abstract>
<identifier type="citekey">alemayehu-etal-2026-amharic</identifier>
<identifier type="doi">10.63317/536jn6g8rjnx</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.627/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7894</start>
<end>7904</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Amharic DBpedia Chapter: A Knowledge Graph for a Low-Resource Language
%A Alemayehu, HIzkiel Mitiku
%A Taffa, Tilahun Abedissa
%A Bayissa, Meti Adane
%A Zewge, Andargachew Asfaw
%A Zahera, Hamada
%A Usbeck, Ricardo
%A Ngonga Ngomo, Axel-Cyrille
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F alemayehu-etal-2026-amharic
%X DBpedia is a community-driven project that extracts structured knowledge from Wikipedia via language-specific chapters. We present the first steps toward the Amharic DBpedia chapter by extending the DBpedia Extraction Framework (DEF) to support Amharic Wikipedia, including language-specific components such as Ethiopian date parsers, an Ethiopian–Gregorian calendar converter, an Arabic–Ge’ez number converter, and Amharic template mappings, together with automated extraction pipelines and the publication of the resulting knowledge graph through a live website, DBpedia Databus collection, and query endpoints. For mapping, we evaluate the zero-shot NLLB-200 translation model on Amharic infobox property names, achieving a BLEU score of 45.31. For ontology alignment, we link mapped properties to DBpedia ontology properties across 58 DBpedia classes and benchmark multilingual encoders with Amharic support, including Afro-XLM-R Base, XLM-R Base, and Amharic fine-tuned mBERT. The fine-tuned Afro-XLM-R model achieves 92.1% Top-10 accuracy and strong ranking performance, as measured by Mean Reciprocal Rank (MRR). We release all resources developed for the Amharic DBpedia chapter, including the Ethiopian date parser, Ethiopian–Gregorian calendar converter, Arabic–Geʽez numeral converter, Amharic template mappings, automated extraction workflows, and the resulting Amharic DBpedia knowledge graph with public access via the DBpedia Databus collection, Tentris query endpoint, and the live website at am.dbpedia.org.
%R 10.63317/536jn6g8rjnx
%U https://aclanthology.org/2026.lrec-1.627/
%U https://doi.org/10.63317/536jn6g8rjnx
%P 7894-7904
Markdown (Informal)
[Amharic DBpedia Chapter: A Knowledge Graph for a Low-Resource Language](https://aclanthology.org/2026.lrec-1.627/) (Alemayehu et al., LREC 2026)
ACL
- HIzkiel Mitiku Alemayehu, Tilahun Abedissa Taffa, Meti Adane Bayissa, Andargachew Asfaw Zewge, Hamada Zahera, Ricardo Usbeck, and Axel-Cyrille Ngonga Ngomo. 2026. Amharic DBpedia Chapter: A Knowledge Graph for a Low-Resource Language. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 7894–7904, Palma de Mallorca, Spain. ELRA Language Resource Association.