@inproceedings{chukwuneke-etal-2022-igbobert,
title = "{I}gbo{BERT} Models: Building and Training Transformer Models for the {I}gbo Language",
author = "Chukwuneke, Chiamaka and
Ezeani, Ignatius and
Rayson, Paul and
El-Haj, Mahmoud",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.547",
pages = "5114--5122",
abstract = "This work presents a standard Igbo named entity recognition (IgboNER) dataset as well as the results from training and fine-tuning state-of-the-art transformer IgboNER models. We discuss the process of our dataset creation - data collection and annotation and quality checking. We also present experimental processes involved in building an IgboBERT language model from scratch as well as fine-tuning it along with other non-Igbo pre-trained models for the downstream IgboNER task. Our results show that, although the IgboNER task benefited hugely from fine-tuning large transformer model, fine-tuning a transformer model built from scratch with comparatively little Igbo text data seems to yield quite decent results for the IgboNER task. This work will contribute immensely to IgboNLP in particular as well as the wider African and low-resource NLP efforts Keywords: Igbo, named entity recognition, BERT models, under-resourced, dataset",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chukwuneke-etal-2022-igbobert">
<titleInfo>
<title>IgboBERT Models: Building and Training Transformer Models for the Igbo Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chiamaka</namePart>
<namePart type="family">Chukwuneke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignatius</namePart>
<namePart type="family">Ezeani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work presents a standard Igbo named entity recognition (IgboNER) dataset as well as the results from training and fine-tuning state-of-the-art transformer IgboNER models. We discuss the process of our dataset creation - data collection and annotation and quality checking. We also present experimental processes involved in building an IgboBERT language model from scratch as well as fine-tuning it along with other non-Igbo pre-trained models for the downstream IgboNER task. Our results show that, although the IgboNER task benefited hugely from fine-tuning large transformer model, fine-tuning a transformer model built from scratch with comparatively little Igbo text data seems to yield quite decent results for the IgboNER task. This work will contribute immensely to IgboNLP in particular as well as the wider African and low-resource NLP efforts Keywords: Igbo, named entity recognition, BERT models, under-resourced, dataset</abstract>
<identifier type="citekey">chukwuneke-etal-2022-igbobert</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.547</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5114</start>
<end>5122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IgboBERT Models: Building and Training Transformer Models for the Igbo Language
%A Chukwuneke, Chiamaka
%A Ezeani, Ignatius
%A Rayson, Paul
%A El-Haj, Mahmoud
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F chukwuneke-etal-2022-igbobert
%X This work presents a standard Igbo named entity recognition (IgboNER) dataset as well as the results from training and fine-tuning state-of-the-art transformer IgboNER models. We discuss the process of our dataset creation - data collection and annotation and quality checking. We also present experimental processes involved in building an IgboBERT language model from scratch as well as fine-tuning it along with other non-Igbo pre-trained models for the downstream IgboNER task. Our results show that, although the IgboNER task benefited hugely from fine-tuning large transformer model, fine-tuning a transformer model built from scratch with comparatively little Igbo text data seems to yield quite decent results for the IgboNER task. This work will contribute immensely to IgboNLP in particular as well as the wider African and low-resource NLP efforts Keywords: Igbo, named entity recognition, BERT models, under-resourced, dataset
%U https://aclanthology.org/2022.lrec-1.547
%P 5114-5122
Markdown (Informal)
[IgboBERT Models: Building and Training Transformer Models for the Igbo Language](https://aclanthology.org/2022.lrec-1.547) (Chukwuneke et al., LREC 2022)
ACL