@inproceedings{hoang-etal-2023-vbd,
title = "{VBD}{\_}{NLP} at {S}em{E}val-2023 Task 2: Named Entity Recognition Systems Enhanced by {B}abel{N}et and {W}ikipedia",
author = "Hoang, Phu Gia and
Thanh, Le and
Trieu, Hai-Long",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.253",
doi = "10.18653/v1/2023.semeval-1.253",
pages = "1833--1843",
abstract = "We describe our systems participated in the SemEval-2023 shared task for Named Entity Recognition (NER) in English and Bangla. In order to address the challenges of the task, where a large number of fine-grained named entity types need to be detected with only a small amount of training data, we use a method to augment the training data based on BabelNet conceptsand Wikipedia redirections to automatically annotate named entities from Wikipedia articles. We build our NER systems based on the powerful mDeBERTa pretrained language model and trained on the augmented data. Our approach significantly enhances the performance of the fine-grained NER task in both English and Bangla subtracks, outperforming the baseline models. Specifically, our augmented systems achieve macro-f1 scores of 52.64{\%} and 64.31{\%}, representing improvements of 2.38{\%} and 11.33{\%} over the English and Bangla baselines, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-etal-2023-vbd">
<titleInfo>
<title>VBD_NLP at SemEval-2023 Task 2: Named Entity Recognition Systems Enhanced by BabelNet and Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phu</namePart>
<namePart type="given">Gia</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Thanh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai-Long</namePart>
<namePart type="family">Trieu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe our systems participated in the SemEval-2023 shared task for Named Entity Recognition (NER) in English and Bangla. In order to address the challenges of the task, where a large number of fine-grained named entity types need to be detected with only a small amount of training data, we use a method to augment the training data based on BabelNet conceptsand Wikipedia redirections to automatically annotate named entities from Wikipedia articles. We build our NER systems based on the powerful mDeBERTa pretrained language model and trained on the augmented data. Our approach significantly enhances the performance of the fine-grained NER task in both English and Bangla subtracks, outperforming the baseline models. Specifically, our augmented systems achieve macro-f1 scores of 52.64% and 64.31%, representing improvements of 2.38% and 11.33% over the English and Bangla baselines, respectively.</abstract>
<identifier type="citekey">hoang-etal-2023-vbd</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.253</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.253</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1833</start>
<end>1843</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VBD_NLP at SemEval-2023 Task 2: Named Entity Recognition Systems Enhanced by BabelNet and Wikipedia
%A Hoang, Phu Gia
%A Thanh, Le
%A Trieu, Hai-Long
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F hoang-etal-2023-vbd
%X We describe our systems participated in the SemEval-2023 shared task for Named Entity Recognition (NER) in English and Bangla. In order to address the challenges of the task, where a large number of fine-grained named entity types need to be detected with only a small amount of training data, we use a method to augment the training data based on BabelNet conceptsand Wikipedia redirections to automatically annotate named entities from Wikipedia articles. We build our NER systems based on the powerful mDeBERTa pretrained language model and trained on the augmented data. Our approach significantly enhances the performance of the fine-grained NER task in both English and Bangla subtracks, outperforming the baseline models. Specifically, our augmented systems achieve macro-f1 scores of 52.64% and 64.31%, representing improvements of 2.38% and 11.33% over the English and Bangla baselines, respectively.
%R 10.18653/v1/2023.semeval-1.253
%U https://aclanthology.org/2023.semeval-1.253
%U https://doi.org/10.18653/v1/2023.semeval-1.253
%P 1833-1843
Markdown (Informal)
[VBD_NLP at SemEval-2023 Task 2: Named Entity Recognition Systems Enhanced by BabelNet and Wikipedia](https://aclanthology.org/2023.semeval-1.253) (Hoang et al., SemEval 2023)
ACL