@inproceedings{dao-etal-2025-overcoming,
title = "Overcoming Data Scarcity in Named Entity Recognition: Synthetic Data Generation with Large Language Models",
author = "Dao, An and
Teranishi, Hiroki and
Matsumoto, Yuji and
Boudin, Florian and
Aizawa, Akiko",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Tsujii, Junichi",
booktitle = "Proceedings of the 24th Workshop on Biomedical Language Processing",
month = aug,
year = "2025",
address = "Viena, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bionlp-1.28/",
doi = "10.18653/v1/2025.bionlp-1.28",
pages = "328--340",
ISBN = "979-8-89176-275-6",
abstract = "Named Entity Recognition (NER) is crucial for extracting domain-specific entities from text, particularly in biomedical and chemical fields. Developing high-quality NER models in specialized domains is challenging due to the limited availability of annotated data, with manual annotation being a key method of data construction. However, manual annotation is time-consuming and requires domain expertise, making it difficult in specialized domains. Traditional data augmentation (DA) techniques also rely on annotated data to some extent, further limiting their effectiveness. In this paper, we propose a novel approach to synthetic data generation for NER using large language models (LLMs) to generate sentences based solely on a set of example entities. This method simplifies the augmentation process and is effective even with a limited set of entities.We evaluate our approach using BERT-based models on the BC4CHEMD, BC5CDR, and TDMSci datasets, demonstrating that synthetic data significantly improves model performance and robustness, particularly in low-resource settings. This work provides a scalable solution for enhancing NER in specialized domains, overcoming the limitations of manual annotation and traditional augmentation methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dao-etal-2025-overcoming">
<titleInfo>
<title>Overcoming Data Scarcity in Named Entity Recognition: Synthetic Data Generation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">An</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Teranishi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Boudin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Workshop on Biomedical Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Viena, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-275-6</identifier>
</relatedItem>
<abstract>Named Entity Recognition (NER) is crucial for extracting domain-specific entities from text, particularly in biomedical and chemical fields. Developing high-quality NER models in specialized domains is challenging due to the limited availability of annotated data, with manual annotation being a key method of data construction. However, manual annotation is time-consuming and requires domain expertise, making it difficult in specialized domains. Traditional data augmentation (DA) techniques also rely on annotated data to some extent, further limiting their effectiveness. In this paper, we propose a novel approach to synthetic data generation for NER using large language models (LLMs) to generate sentences based solely on a set of example entities. This method simplifies the augmentation process and is effective even with a limited set of entities.We evaluate our approach using BERT-based models on the BC4CHEMD, BC5CDR, and TDMSci datasets, demonstrating that synthetic data significantly improves model performance and robustness, particularly in low-resource settings. This work provides a scalable solution for enhancing NER in specialized domains, overcoming the limitations of manual annotation and traditional augmentation methods.</abstract>
<identifier type="citekey">dao-etal-2025-overcoming</identifier>
<identifier type="doi">10.18653/v1/2025.bionlp-1.28</identifier>
<location>
<url>https://aclanthology.org/2025.bionlp-1.28/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>328</start>
<end>340</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overcoming Data Scarcity in Named Entity Recognition: Synthetic Data Generation with Large Language Models
%A Dao, An
%A Teranishi, Hiroki
%A Matsumoto, Yuji
%A Boudin, Florian
%A Aizawa, Akiko
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Tsujii, Junichi
%S Proceedings of the 24th Workshop on Biomedical Language Processing
%D 2025
%8 August
%I Association for Computational Linguistics
%C Viena, Austria
%@ 979-8-89176-275-6
%F dao-etal-2025-overcoming
%X Named Entity Recognition (NER) is crucial for extracting domain-specific entities from text, particularly in biomedical and chemical fields. Developing high-quality NER models in specialized domains is challenging due to the limited availability of annotated data, with manual annotation being a key method of data construction. However, manual annotation is time-consuming and requires domain expertise, making it difficult in specialized domains. Traditional data augmentation (DA) techniques also rely on annotated data to some extent, further limiting their effectiveness. In this paper, we propose a novel approach to synthetic data generation for NER using large language models (LLMs) to generate sentences based solely on a set of example entities. This method simplifies the augmentation process and is effective even with a limited set of entities.We evaluate our approach using BERT-based models on the BC4CHEMD, BC5CDR, and TDMSci datasets, demonstrating that synthetic data significantly improves model performance and robustness, particularly in low-resource settings. This work provides a scalable solution for enhancing NER in specialized domains, overcoming the limitations of manual annotation and traditional augmentation methods.
%R 10.18653/v1/2025.bionlp-1.28
%U https://aclanthology.org/2025.bionlp-1.28/
%U https://doi.org/10.18653/v1/2025.bionlp-1.28
%P 328-340
Markdown (Informal)
[Overcoming Data Scarcity in Named Entity Recognition: Synthetic Data Generation with Large Language Models](https://aclanthology.org/2025.bionlp-1.28/) (Dao et al., BioNLP 2025)
ACL