@inproceedings{kamath-vajjala-2025-synthetic,
title = "Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?",
author = "Kamath, Gaurav and
Vajjala, Sowmya",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-short.15/",
pages = "159--167",
ISBN = "979-8-89176-299-2",
abstract = "We explore whether synthetic datasets generated by large language models using a few high quality seed samples are useful for low-resource named entity recognition, considering 11 languages from three language families. Our results suggest that synthetic data created with such seed data is a reasonable choice when there is no available labeled data, and is better than using entirely automatically labeled data. However, a small amount of high-quality data, coupled with cross-lingual transfer from a related language, always offers better performance. Data and code available at: https://github.com/grvkamath/low-resource-syn-ner."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamath-vajjala-2025-synthetic">
<titleInfo>
<title>Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Kamath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sowmya</namePart>
<namePart type="family">Vajjala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-299-2</identifier>
</relatedItem>
<abstract>We explore whether synthetic datasets generated by large language models using a few high quality seed samples are useful for low-resource named entity recognition, considering 11 languages from three language families. Our results suggest that synthetic data created with such seed data is a reasonable choice when there is no available labeled data, and is better than using entirely automatically labeled data. However, a small amount of high-quality data, coupled with cross-lingual transfer from a related language, always offers better performance. Data and code available at: https://github.com/grvkamath/low-resource-syn-ner.</abstract>
<identifier type="citekey">kamath-vajjala-2025-synthetic</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-short.15/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>159</start>
<end>167</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?
%A Kamath, Gaurav
%A Vajjala, Sowmya
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-299-2
%F kamath-vajjala-2025-synthetic
%X We explore whether synthetic datasets generated by large language models using a few high quality seed samples are useful for low-resource named entity recognition, considering 11 languages from three language families. Our results suggest that synthetic data created with such seed data is a reasonable choice when there is no available labeled data, and is better than using entirely automatically labeled data. However, a small amount of high-quality data, coupled with cross-lingual transfer from a related language, always offers better performance. Data and code available at: https://github.com/grvkamath/low-resource-syn-ner.
%U https://aclanthology.org/2025.ijcnlp-short.15/
%P 159-167
Markdown (Informal)
[Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?](https://aclanthology.org/2025.ijcnlp-short.15/) (Kamath & Vajjala, IJCNLP-AACL 2025)
ACL
- Gaurav Kamath and Sowmya Vajjala. 2025. Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 159–167, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.