@inproceedings{kaushik-etal-2026-aptfiner,
title = "{APTF}i{NER}: Annotation Preserving Translation for Fine-grained Named Entity Recognition",
author = "Kaushik, Prachuryya and
Gupta, Adittya and
Maurya, Ajanta and
Sharma, Gautam and
Saradhi, V. Vijaya and
Anand, Ashish",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.608/",
doi = "10.63317/3w7rv4rg7nty",
pages = "7668--7680",
abstract = "We present APTFiNER, a novel fine-grained named entity recognition (FgNER) dataset covering six low-resource Indian languages spoken by over 400 million people across various nations. While creating FgNER resources through manual annotation is typically expensive and labor-intensive, distant supervision has emerged as a workable alternative. Yet, such FgNER datasets are often noisy, as each entity mentions are often assigned multiple entity types, which necessitates computationally demanding noise-aware models. Furthermore, resources for both coarse-grained and fine-grained NER tasks remain scarce for low-resource languages. To overcome this scarcity, we utilized the superior reasoning and translation capability of Gemini through the proposed annotation-preserving translation method and created a large-scale FgNER dataset comprising over 411 thousand sentences, 697 thousand entity mentions, and 5.8 million tokens in total. We translated the MultiCoNER2 English FgNER dataset to the target languages: \textit{Assamese (as)}, \textit{Marathi (mr)}, \textit{Nepali (ne)}, \textit{Tamil (ta)}, \textit{Telugu (te)}, and a vulnerable language, \textit{Bodo (brx)}. Through rigorous analyses and human evaluations, the effectiveness of our method and the high quality of the resulting dataset are ascertained with F1 score improvements of 8{\%} in both Tamil and Telugu, and 25{\%} in Marathi over the current state-of-the-art. The dataset, expert detector models, the agentic tool, and the interactive web application are available as open-source resources at: \href{https://hf.co/collections/prachuryyaIITG/aptfiner}{https://hf.co/collections/prachuryyaIITG/aptfiner}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaushik-etal-2026-aptfiner">
<titleInfo>
<title>APTFiNER: Annotation Preserving Translation for Fine-grained Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prachuryya</namePart>
<namePart type="family">Kaushik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adittya</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajanta</namePart>
<namePart type="family">Maurya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gautam</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">V</namePart>
<namePart type="given">Vijaya</namePart>
<namePart type="family">Saradhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Anand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present APTFiNER, a novel fine-grained named entity recognition (FgNER) dataset covering six low-resource Indian languages spoken by over 400 million people across various nations. While creating FgNER resources through manual annotation is typically expensive and labor-intensive, distant supervision has emerged as a workable alternative. Yet, such FgNER datasets are often noisy, as each entity mentions are often assigned multiple entity types, which necessitates computationally demanding noise-aware models. Furthermore, resources for both coarse-grained and fine-grained NER tasks remain scarce for low-resource languages. To overcome this scarcity, we utilized the superior reasoning and translation capability of Gemini through the proposed annotation-preserving translation method and created a large-scale FgNER dataset comprising over 411 thousand sentences, 697 thousand entity mentions, and 5.8 million tokens in total. We translated the MultiCoNER2 English FgNER dataset to the target languages: Assamese (as), Marathi (mr), Nepali (ne), Tamil (ta), Telugu (te), and a vulnerable language, Bodo (brx). Through rigorous analyses and human evaluations, the effectiveness of our method and the high quality of the resulting dataset are ascertained with F1 score improvements of 8% in both Tamil and Telugu, and 25% in Marathi over the current state-of-the-art. The dataset, expert detector models, the agentic tool, and the interactive web application are available as open-source resources at: \hrefhttps://hf.co/collections/prachuryyaIITG/aptfinerhttps://hf.co/collections/prachuryyaIITG/aptfiner.</abstract>
<identifier type="citekey">kaushik-etal-2026-aptfiner</identifier>
<identifier type="doi">10.63317/3w7rv4rg7nty</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.608/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7668</start>
<end>7680</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T APTFiNER: Annotation Preserving Translation for Fine-grained Named Entity Recognition
%A Kaushik, Prachuryya
%A Gupta, Adittya
%A Maurya, Ajanta
%A Sharma, Gautam
%A Saradhi, V. Vijaya
%A Anand, Ashish
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F kaushik-etal-2026-aptfiner
%X We present APTFiNER, a novel fine-grained named entity recognition (FgNER) dataset covering six low-resource Indian languages spoken by over 400 million people across various nations. While creating FgNER resources through manual annotation is typically expensive and labor-intensive, distant supervision has emerged as a workable alternative. Yet, such FgNER datasets are often noisy, as each entity mentions are often assigned multiple entity types, which necessitates computationally demanding noise-aware models. Furthermore, resources for both coarse-grained and fine-grained NER tasks remain scarce for low-resource languages. To overcome this scarcity, we utilized the superior reasoning and translation capability of Gemini through the proposed annotation-preserving translation method and created a large-scale FgNER dataset comprising over 411 thousand sentences, 697 thousand entity mentions, and 5.8 million tokens in total. We translated the MultiCoNER2 English FgNER dataset to the target languages: Assamese (as), Marathi (mr), Nepali (ne), Tamil (ta), Telugu (te), and a vulnerable language, Bodo (brx). Through rigorous analyses and human evaluations, the effectiveness of our method and the high quality of the resulting dataset are ascertained with F1 score improvements of 8% in both Tamil and Telugu, and 25% in Marathi over the current state-of-the-art. The dataset, expert detector models, the agentic tool, and the interactive web application are available as open-source resources at: \hrefhttps://hf.co/collections/prachuryyaIITG/aptfinerhttps://hf.co/collections/prachuryyaIITG/aptfiner.
%R 10.63317/3w7rv4rg7nty
%U https://aclanthology.org/2026.lrec-1.608/
%U https://doi.org/10.63317/3w7rv4rg7nty
%P 7668-7680
Markdown (Informal)
[APTFiNER: Annotation Preserving Translation for Fine-grained Named Entity Recognition](https://aclanthology.org/2026.lrec-1.608/) (Kaushik et al., LREC 2026)
ACL