@inproceedings{moreira-etal-2026-data,
title = "Data Augmentation for Named Entity Recognition in Domain-Specific Scenarios in {P}ortuguese",
author = "Moreira, Higor and
Silva, Patricia Ferreira da and
Bencke, Luciana and
Moreira, Viviane",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-1.25/",
pages = "250--259",
ISBN = "979-8-89176-387-6",
abstract = "Named Entity Recognition (NER) is an important task of Natural Language Processing. Achieving good results in this task usually requires a large amount of labeled data to train models. This is especially difficult in domain-specific datasets and low-resourced languages. To mitigate the high cost of human-annotated data, data augmentation can be used. In this work, we evaluate Data Augmentation techniques for NER, focusing on domain-specific datasets in Portuguese.We employed augmentation techniques based on rules, back-translation, and large language models on four datasets of varying sizes to train Transformer-based NER models.The results showed that most techniques improved over the baseline, with the best results achieved using PP-LLM, SR, and MR."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moreira-etal-2026-data">
<titleInfo>
<title>Data Augmentation for Named Entity Recognition in Domain-Specific Scenarios in Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Higor</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="given">Ferreira</namePart>
<namePart type="given">da</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Bencke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>Named Entity Recognition (NER) is an important task of Natural Language Processing. Achieving good results in this task usually requires a large amount of labeled data to train models. This is especially difficult in domain-specific datasets and low-resourced languages. To mitigate the high cost of human-annotated data, data augmentation can be used. In this work, we evaluate Data Augmentation techniques for NER, focusing on domain-specific datasets in Portuguese.We employed augmentation techniques based on rules, back-translation, and large language models on four datasets of varying sizes to train Transformer-based NER models.The results showed that most techniques improved over the baseline, with the best results achieved using PP-LLM, SR, and MR.</abstract>
<identifier type="citekey">moreira-etal-2026-data</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.25/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>250</start>
<end>259</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation for Named Entity Recognition in Domain-Specific Scenarios in Portuguese
%A Moreira, Higor
%A Silva, Patricia Ferreira da
%A Bencke, Luciana
%A Moreira, Viviane
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F moreira-etal-2026-data
%X Named Entity Recognition (NER) is an important task of Natural Language Processing. Achieving good results in this task usually requires a large amount of labeled data to train models. This is especially difficult in domain-specific datasets and low-resourced languages. To mitigate the high cost of human-annotated data, data augmentation can be used. In this work, we evaluate Data Augmentation techniques for NER, focusing on domain-specific datasets in Portuguese.We employed augmentation techniques based on rules, back-translation, and large language models on four datasets of varying sizes to train Transformer-based NER models.The results showed that most techniques improved over the baseline, with the best results achieved using PP-LLM, SR, and MR.
%U https://aclanthology.org/2026.propor-1.25/
%P 250-259
Markdown (Informal)
[Data Augmentation for Named Entity Recognition in Domain-Specific Scenarios in Portuguese](https://aclanthology.org/2026.propor-1.25/) (Moreira et al., PROPOR 2026)
ACL