MphayaNER: Named Entity Recognition for Tshivenda

MphayaNER: Named Entity Recognition for Tshivenda

Named Entity Recognition (NER) plays a vital role in various Natural Language Processing tasks such as information retrieval, text classification, and question answering. However, NER can be challenging, especially in low-resource languages with limited annotated datasets and tools. This paper adds...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mbuvha, Rendani, Adelani, David I, Mutavhatsindi, Tendani, Rakhuhu, Tshimangadzo, Mauda, Aluwani, Maumela, Tshifhiwa Joshua, Masindi, Andisani, Rananga, Seani, Marivate, Vukosi, Marwala, Tshilidzi
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Mbuvha, Rendani
Adelani, David I
Mutavhatsindi, Tendani
Rakhuhu, Tshimangadzo
Mauda, Aluwani
Maumela, Tshifhiwa Joshua
Masindi, Andisani
Rananga, Seani
Marivate, Vukosi
Marwala, Tshilidzi
description Named Entity Recognition (NER) plays a vital role in various Natural Language Processing tasks such as information retrieval, text classification, and question answering. However, NER can be challenging, especially in low-resource languages with limited annotated datasets and tools. This paper adds to the effort of addressing these challenges by introducing MphayaNER, the first Tshivenda NER corpus in the news domain. We establish NER baselines by \textit{fine-tuning} state-of-the-art models on MphayaNER. The study also explores zero-shot transfer between Tshivenda and other related Bantu languages, with chiShona and Kiswahili showing the best results. Augmenting MphayaNER with chiShona data was also found to improve model performance significantly. Both MphayaNER and the baseline models are made publicly available.
doi_str_mv 10.48550/arxiv.2304.03952
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2304_03952</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2304_03952</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-8116151876874d127f684cf60136e1bf73e867429715284803ed595c8ec077c43</originalsourceid><addsrcrecordid>eNotzr1uwjAUQGEvDBX0ATrVL5DU13_3hq1CaUECKqHskXFssAQJChFq3r4qMJ3t6GPsDUSuyRjx4frfdMulEjoXqjDyhcHmcnSj25a7Od-6c2h42Q5pGPku-O7QpiF1LY9dz6vrMd1C27gZm0R3uobXZ6es-iqrxTJb_3yvFp_rzFmUGQFYMEBoCXUDEqMl7aMVoGyAfUQVyKKWBYKRpEmo0JjCeApeIHqtpuz9sb2b60ufzq4f6397fberP47vO-Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>MphayaNER: Named Entity Recognition for Tshivenda</title><source>arXiv.org</source><creator>Mbuvha, Rendani ; Adelani, David I ; Mutavhatsindi, Tendani ; Rakhuhu, Tshimangadzo ; Mauda, Aluwani ; Maumela, Tshifhiwa Joshua ; Masindi, Andisani ; Rananga, Seani ; Marivate, Vukosi ; Marwala, Tshilidzi</creator><creatorcontrib>Mbuvha, Rendani ; Adelani, David I ; Mutavhatsindi, Tendani ; Rakhuhu, Tshimangadzo ; Mauda, Aluwani ; Maumela, Tshifhiwa Joshua ; Masindi, Andisani ; Rananga, Seani ; Marivate, Vukosi ; Marwala, Tshilidzi</creatorcontrib><description>Named Entity Recognition (NER) plays a vital role in various Natural Language Processing tasks such as information retrieval, text classification, and question answering. However, NER can be challenging, especially in low-resource languages with limited annotated datasets and tools. This paper adds to the effort of addressing these challenges by introducing MphayaNER, the first Tshivenda NER corpus in the news domain. We establish NER baselines by \textit{fine-tuning} state-of-the-art models on MphayaNER. The study also explores zero-shot transfer between Tshivenda and other related Bantu languages, with chiShona and Kiswahili showing the best results. Augmenting MphayaNER with chiShona data was also found to improve model performance significantly. Both MphayaNER and the baseline models are made publicly available.</description><identifier>DOI: 10.48550/arxiv.2304.03952</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language</subject><creationdate>2023-04</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2304.03952$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2304.03952$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Mbuvha, Rendani</creatorcontrib><creatorcontrib>Adelani, David I</creatorcontrib><creatorcontrib>Mutavhatsindi, Tendani</creatorcontrib><creatorcontrib>Rakhuhu, Tshimangadzo</creatorcontrib><creatorcontrib>Mauda, Aluwani</creatorcontrib><creatorcontrib>Maumela, Tshifhiwa Joshua</creatorcontrib><creatorcontrib>Masindi, Andisani</creatorcontrib><creatorcontrib>Rananga, Seani</creatorcontrib><creatorcontrib>Marivate, Vukosi</creatorcontrib><creatorcontrib>Marwala, Tshilidzi</creatorcontrib><title>MphayaNER: Named Entity Recognition for Tshivenda</title><description>Named Entity Recognition (NER) plays a vital role in various Natural Language Processing tasks such as information retrieval, text classification, and question answering. However, NER can be challenging, especially in low-resource languages with limited annotated datasets and tools. This paper adds to the effort of addressing these challenges by introducing MphayaNER, the first Tshivenda NER corpus in the news domain. We establish NER baselines by \textit{fine-tuning} state-of-the-art models on MphayaNER. The study also explores zero-shot transfer between Tshivenda and other related Bantu languages, with chiShona and Kiswahili showing the best results. Augmenting MphayaNER with chiShona data was also found to improve model performance significantly. Both MphayaNER and the baseline models are made publicly available.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr1uwjAUQGEvDBX0ATrVL5DU13_3hq1CaUECKqHskXFssAQJChFq3r4qMJ3t6GPsDUSuyRjx4frfdMulEjoXqjDyhcHmcnSj25a7Od-6c2h42Q5pGPku-O7QpiF1LY9dz6vrMd1C27gZm0R3uobXZ6es-iqrxTJb_3yvFp_rzFmUGQFYMEBoCXUDEqMl7aMVoGyAfUQVyKKWBYKRpEmo0JjCeApeIHqtpuz9sb2b60ufzq4f6397fberP47vO-Q</recordid><startdate>20230408</startdate><enddate>20230408</enddate><creator>Mbuvha, Rendani</creator><creator>Adelani, David I</creator><creator>Mutavhatsindi, Tendani</creator><creator>Rakhuhu, Tshimangadzo</creator><creator>Mauda, Aluwani</creator><creator>Maumela, Tshifhiwa Joshua</creator><creator>Masindi, Andisani</creator><creator>Rananga, Seani</creator><creator>Marivate, Vukosi</creator><creator>Marwala, Tshilidzi</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230408</creationdate><title>MphayaNER: Named Entity Recognition for Tshivenda</title><author>Mbuvha, Rendani ; Adelani, David I ; Mutavhatsindi, Tendani ; Rakhuhu, Tshimangadzo ; Mauda, Aluwani ; Maumela, Tshifhiwa Joshua ; Masindi, Andisani ; Rananga, Seani ; Marivate, Vukosi ; Marwala, Tshilidzi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-8116151876874d127f684cf60136e1bf73e867429715284803ed595c8ec077c43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Mbuvha, Rendani</creatorcontrib><creatorcontrib>Adelani, David I</creatorcontrib><creatorcontrib>Mutavhatsindi, Tendani</creatorcontrib><creatorcontrib>Rakhuhu, Tshimangadzo</creatorcontrib><creatorcontrib>Mauda, Aluwani</creatorcontrib><creatorcontrib>Maumela, Tshifhiwa Joshua</creatorcontrib><creatorcontrib>Masindi, Andisani</creatorcontrib><creatorcontrib>Rananga, Seani</creatorcontrib><creatorcontrib>Marivate, Vukosi</creatorcontrib><creatorcontrib>Marwala, Tshilidzi</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Mbuvha, Rendani</au><au>Adelani, David I</au><au>Mutavhatsindi, Tendani</au><au>Rakhuhu, Tshimangadzo</au><au>Mauda, Aluwani</au><au>Maumela, Tshifhiwa Joshua</au><au>Masindi, Andisani</au><au>Rananga, Seani</au><au>Marivate, Vukosi</au><au>Marwala, Tshilidzi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>MphayaNER: Named Entity Recognition for Tshivenda</atitle><date>2023-04-08</date><risdate>2023</risdate><abstract>Named Entity Recognition (NER) plays a vital role in various Natural Language Processing tasks such as information retrieval, text classification, and question answering. However, NER can be challenging, especially in low-resource languages with limited annotated datasets and tools. This paper adds to the effort of addressing these challenges by introducing MphayaNER, the first Tshivenda NER corpus in the news domain. We establish NER baselines by \textit{fine-tuning} state-of-the-art models on MphayaNER. The study also explores zero-shot transfer between Tshivenda and other related Bantu languages, with chiShona and Kiswahili showing the best results. Augmenting MphayaNER with chiShona data was also found to improve model performance significantly. Both MphayaNER and the baseline models are made publicly available.</abstract><doi>10.48550/arxiv.2304.03952</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2304.03952
ispartof
issn
language eng
recordid cdi_arxiv_primary_2304_03952
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computation and Language
title MphayaNER: Named Entity Recognition for Tshivenda
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T19%3A07%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=MphayaNER:%20Named%20Entity%20Recognition%20for%20Tshivenda&rft.au=Mbuvha,%20Rendani&rft.date=2023-04-08&rft_id=info:doi/10.48550/arxiv.2304.03952&rft_dat=%3Carxiv_GOX%3E2304_03952%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true