@inproceedings{nzeyimana-niyongabo-rubungo-2022-kinyabert,
title = "{K}inya{BERT}: a Morphology-aware {K}inyarwanda Language Model",
author = "Nzeyimana, Antoine and
Niyongabo Rubungo, Andre",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.367",
doi = "10.18653/v1/2022.acl-long.367",
pages = "5347--5363",
abstract = "Pre-trained language models such as BERT have been successful at tackling many natural language processing tasks. However, the unsupervised sub-word tokenization methods commonly used in these models (e.g., byte-pair encoding - BPE) are sub-optimal at handling morphologically rich languages. Even given a morphological analyzer, naive sequencing of morphemes into a standard BERT architecture is inefficient at capturing morphological compositionality and expressing word-relative syntactic regularities. We address these challenges by proposing a simple yet effective two-tier BERT architecture that leverages a morphological analyzer and explicitly represents morphological compositionality.Despite the success of BERT, most of its evaluations have been conducted on high-resource languages, obscuring its applicability on low-resource languages. We evaluate our proposed method on the low-resource morphologically rich Kinyarwanda language, naming the proposed model architecture KinyaBERT. A robust set of experimental results reveal that KinyaBERT outperforms solid baselines by 2{\%} in F1 score on a named entity recognition task and by 4.3{\%} in average score of a machine-translated GLUE benchmark. KinyaBERT fine-tuning has better convergence and achieves more robust results on multiple tasks even in the presence of translation noise.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nzeyimana-niyongabo-rubungo-2022-kinyabert">
<titleInfo>
<title>KinyaBERT: a Morphology-aware Kinyarwanda Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Nzeyimana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Niyongabo Rubungo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models such as BERT have been successful at tackling many natural language processing tasks. However, the unsupervised sub-word tokenization methods commonly used in these models (e.g., byte-pair encoding - BPE) are sub-optimal at handling morphologically rich languages. Even given a morphological analyzer, naive sequencing of morphemes into a standard BERT architecture is inefficient at capturing morphological compositionality and expressing word-relative syntactic regularities. We address these challenges by proposing a simple yet effective two-tier BERT architecture that leverages a morphological analyzer and explicitly represents morphological compositionality.Despite the success of BERT, most of its evaluations have been conducted on high-resource languages, obscuring its applicability on low-resource languages. We evaluate our proposed method on the low-resource morphologically rich Kinyarwanda language, naming the proposed model architecture KinyaBERT. A robust set of experimental results reveal that KinyaBERT outperforms solid baselines by 2% in F1 score on a named entity recognition task and by 4.3% in average score of a machine-translated GLUE benchmark. KinyaBERT fine-tuning has better convergence and achieves more robust results on multiple tasks even in the presence of translation noise.</abstract>
<identifier type="citekey">nzeyimana-niyongabo-rubungo-2022-kinyabert</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.367</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.367</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>5347</start>
<end>5363</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KinyaBERT: a Morphology-aware Kinyarwanda Language Model
%A Nzeyimana, Antoine
%A Niyongabo Rubungo, Andre
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F nzeyimana-niyongabo-rubungo-2022-kinyabert
%X Pre-trained language models such as BERT have been successful at tackling many natural language processing tasks. However, the unsupervised sub-word tokenization methods commonly used in these models (e.g., byte-pair encoding - BPE) are sub-optimal at handling morphologically rich languages. Even given a morphological analyzer, naive sequencing of morphemes into a standard BERT architecture is inefficient at capturing morphological compositionality and expressing word-relative syntactic regularities. We address these challenges by proposing a simple yet effective two-tier BERT architecture that leverages a morphological analyzer and explicitly represents morphological compositionality.Despite the success of BERT, most of its evaluations have been conducted on high-resource languages, obscuring its applicability on low-resource languages. We evaluate our proposed method on the low-resource morphologically rich Kinyarwanda language, naming the proposed model architecture KinyaBERT. A robust set of experimental results reveal that KinyaBERT outperforms solid baselines by 2% in F1 score on a named entity recognition task and by 4.3% in average score of a machine-translated GLUE benchmark. KinyaBERT fine-tuning has better convergence and achieves more robust results on multiple tasks even in the presence of translation noise.
%R 10.18653/v1/2022.acl-long.367
%U https://aclanthology.org/2022.acl-long.367
%U https://doi.org/10.18653/v1/2022.acl-long.367
%P 5347-5363
Markdown (Informal)
[KinyaBERT: a Morphology-aware Kinyarwanda Language Model](https://aclanthology.org/2022.acl-long.367) (Nzeyimana & Niyongabo Rubungo, ACL 2022)
ACL
- Antoine Nzeyimana and Andre Niyongabo Rubungo. 2022. KinyaBERT: a Morphology-aware Kinyarwanda Language Model. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5347–5363, Dublin, Ireland. Association for Computational Linguistics.