@inproceedings{adenuga-2026-morpho,
title = "A Morpho-Syntactically Annotated Corpus of {\`O}g{\`e} Folk Narratives with a Focus on Nominal Structure",
author = "Adenuga, Priscilla",
editor = "Matfunjwa, Muzi and
Setaka, Mmasibidi and
Mabuya, Rooweither and
van Zaanen, Menno",
booktitle = "Proceedings of Resources for {A}frican Indigenous Languages ({RAIL}) 2026 @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.rail-1.1/",
doi = "10.63317/22aco7jqqkan",
pages = "1--6",
abstract = "This paper presents a manually annotated morpho-syntactic corpus of {\`O}g{\`e}, an under-resourced indigenous language spoken in Nigeria. The corpus consists of ten folk narratives (approximately 4,667 tokens) collected for the investigation of nominal structure. Annotation is expert-driven and includes token-level part-of-speech tagging together with a structured Determiner Phrase (DP) classification framework designed to capture language-specific nominal configurations. The scheme distinguishes between bare nouns and modified noun phrases, reflecting a central structural property of {\`O}g{\`e}: noun forms remain morphologically stable across contexts, while modifiers exhibit formal and positional variation contributing to reference, specificity, and discourse prominence. The DP classification layer encodes both simple and complex nominal constructions, enabling systematic analysis of internal phrase structure. Designed as a reusable digital resource, the corpus supports morphosyntactic tagging, noun phrase boundary detection, and modeling of nominal structure in low-resource NLP settings. The annotated dataset will be made publicly available through the SADiLaR repository. This work demonstrates how descriptive linguistic analysis can inform annotation design and provides a replicable framework for developing structured resources for under-resourced African languages. Keywords: {\`O}g{\`e}, low-resource NLP, annotated corpus, nominal structure, African languages"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adenuga-2026-morpho">
<titleInfo>
<title>A Morpho-Syntactically Annotated Corpus of Ògè Folk Narratives with a Focus on Nominal Structure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Priscilla</namePart>
<namePart type="family">Adenuga</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 Resources for African Indigenous Languages (RAIL) 2026 @ LREC 2026</title>
</titleInfo>
<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">Rooweither</namePart>
<namePart type="family">Mabuya</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 Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a manually annotated morpho-syntactic corpus of Ògè, an under-resourced indigenous language spoken in Nigeria. The corpus consists of ten folk narratives (approximately 4,667 tokens) collected for the investigation of nominal structure. Annotation is expert-driven and includes token-level part-of-speech tagging together with a structured Determiner Phrase (DP) classification framework designed to capture language-specific nominal configurations. The scheme distinguishes between bare nouns and modified noun phrases, reflecting a central structural property of Ògè: noun forms remain morphologically stable across contexts, while modifiers exhibit formal and positional variation contributing to reference, specificity, and discourse prominence. The DP classification layer encodes both simple and complex nominal constructions, enabling systematic analysis of internal phrase structure. Designed as a reusable digital resource, the corpus supports morphosyntactic tagging, noun phrase boundary detection, and modeling of nominal structure in low-resource NLP settings. The annotated dataset will be made publicly available through the SADiLaR repository. This work demonstrates how descriptive linguistic analysis can inform annotation design and provides a replicable framework for developing structured resources for under-resourced African languages. Keywords: Ògè, low-resource NLP, annotated corpus, nominal structure, African languages</abstract>
<identifier type="citekey">adenuga-2026-morpho</identifier>
<identifier type="doi">10.63317/22aco7jqqkan</identifier>
<location>
<url>https://aclanthology.org/2026.rail-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>6</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Morpho-Syntactically Annotated Corpus of Ògè Folk Narratives with a Focus on Nominal Structure
%A Adenuga, Priscilla
%Y Matfunjwa, Muzi
%Y Setaka, Mmasibidi
%Y Mabuya, Rooweither
%Y van Zaanen, Menno
%S Proceedings of Resources for African Indigenous Languages (RAIL) 2026 @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F adenuga-2026-morpho
%X This paper presents a manually annotated morpho-syntactic corpus of Ògè, an under-resourced indigenous language spoken in Nigeria. The corpus consists of ten folk narratives (approximately 4,667 tokens) collected for the investigation of nominal structure. Annotation is expert-driven and includes token-level part-of-speech tagging together with a structured Determiner Phrase (DP) classification framework designed to capture language-specific nominal configurations. The scheme distinguishes between bare nouns and modified noun phrases, reflecting a central structural property of Ògè: noun forms remain morphologically stable across contexts, while modifiers exhibit formal and positional variation contributing to reference, specificity, and discourse prominence. The DP classification layer encodes both simple and complex nominal constructions, enabling systematic analysis of internal phrase structure. Designed as a reusable digital resource, the corpus supports morphosyntactic tagging, noun phrase boundary detection, and modeling of nominal structure in low-resource NLP settings. The annotated dataset will be made publicly available through the SADiLaR repository. This work demonstrates how descriptive linguistic analysis can inform annotation design and provides a replicable framework for developing structured resources for under-resourced African languages. Keywords: Ògè, low-resource NLP, annotated corpus, nominal structure, African languages
%R 10.63317/22aco7jqqkan
%U https://aclanthology.org/2026.rail-1.1/
%U https://doi.org/10.63317/22aco7jqqkan
%P 1-6
Markdown (Informal)
[A Morpho-Syntactically Annotated Corpus of Ògè Folk Narratives with a Focus on Nominal Structure](https://aclanthology.org/2026.rail-1.1/) (Adenuga, RAIL 2026)
ACL