@inproceedings{ikonic-nesic-etal-2025-zero,
title = "From Zero to Hero: Building {S}erbian {NER} from Rules to {LLM}s",
author = "Ikoni{\'c} Ne{\v{s}}i{\'c}, Milica and
Petalinkar, Sasa and
Stankovi{\'c}, Ranka and
Mitkov, Ruslan",
editor = "Picazo-Izquierdo, Alicia and
Estevanell-Valladares, Ernesto Luis and
Mitkov, Ruslan and
Guillena, Rafael Mu{\~n}oz and
Cerd{\'a}, Ra{\'u}l Garc{\'i}a",
booktitle = "Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.r2lm-1.10/",
pages = "87--96",
abstract = "Named Entity Recognition (NER) presents specific challenges in Serbian, a morphologically rich language. To address these challenges, a comparative evaluation of distinct model paradigms across diverse text genres was conducted. A rule-based system (SrpNER), a traditional deep learning model (Convolutional Neural Network {--} CNN), fine-tuned transformer architectures (Jerteh and Tesla), and Large Language Models (LLMs), specifically ChatGPT 4.0 Nano and 4.1 Mini, were evaluated and compared. For the LLMs, a one-shot prompt engineering approach was employed, using prompt instructions aligned with the entity type definitions used in the manual annotation guidelines. Evaluation was performed on three Serbian datasets representing varied domains: newspaper articles, history textbook excerpts, and a sample of literary texts from the srpELTeC collection. The highest performance was consistently achieved by the fine-tuned transformer models, with F1 scores ranging from 0.78 on newspaper articles to 0.96 on primary school history textbook sample."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ikonic-nesic-etal-2025-zero">
<titleInfo>
<title>From Zero to Hero: Building Serbian NER from Rules to LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Ikonić Nešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sasa</namePart>
<namePart type="family">Petalinkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ranka</namePart>
<namePart type="family">Stanković</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">Muñoz</namePart>
<namePart type="family">Guillena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="given">García</namePart>
<namePart type="family">Cerdá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entity Recognition (NER) presents specific challenges in Serbian, a morphologically rich language. To address these challenges, a comparative evaluation of distinct model paradigms across diverse text genres was conducted. A rule-based system (SrpNER), a traditional deep learning model (Convolutional Neural Network – CNN), fine-tuned transformer architectures (Jerteh and Tesla), and Large Language Models (LLMs), specifically ChatGPT 4.0 Nano and 4.1 Mini, were evaluated and compared. For the LLMs, a one-shot prompt engineering approach was employed, using prompt instructions aligned with the entity type definitions used in the manual annotation guidelines. Evaluation was performed on three Serbian datasets representing varied domains: newspaper articles, history textbook excerpts, and a sample of literary texts from the srpELTeC collection. The highest performance was consistently achieved by the fine-tuned transformer models, with F1 scores ranging from 0.78 on newspaper articles to 0.96 on primary school history textbook sample.</abstract>
<identifier type="citekey">ikonic-nesic-etal-2025-zero</identifier>
<location>
<url>https://aclanthology.org/2025.r2lm-1.10/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>87</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Zero to Hero: Building Serbian NER from Rules to LLMs
%A Ikonić Nešić, Milica
%A Petalinkar, Sasa
%A Stanković, Ranka
%A Mitkov, Ruslan
%Y Picazo-Izquierdo, Alicia
%Y Estevanell-Valladares, Ernesto Luis
%Y Mitkov, Ruslan
%Y Guillena, Rafael Muñoz
%Y Cerdá, Raúl García
%S Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F ikonic-nesic-etal-2025-zero
%X Named Entity Recognition (NER) presents specific challenges in Serbian, a morphologically rich language. To address these challenges, a comparative evaluation of distinct model paradigms across diverse text genres was conducted. A rule-based system (SrpNER), a traditional deep learning model (Convolutional Neural Network – CNN), fine-tuned transformer architectures (Jerteh and Tesla), and Large Language Models (LLMs), specifically ChatGPT 4.0 Nano and 4.1 Mini, were evaluated and compared. For the LLMs, a one-shot prompt engineering approach was employed, using prompt instructions aligned with the entity type definitions used in the manual annotation guidelines. Evaluation was performed on three Serbian datasets representing varied domains: newspaper articles, history textbook excerpts, and a sample of literary texts from the srpELTeC collection. The highest performance was consistently achieved by the fine-tuned transformer models, with F1 scores ranging from 0.78 on newspaper articles to 0.96 on primary school history textbook sample.
%U https://aclanthology.org/2025.r2lm-1.10/
%P 87-96
Markdown (Informal)
[From Zero to Hero: Building Serbian NER from Rules to LLMs](https://aclanthology.org/2025.r2lm-1.10/) (Ikonić Nešić et al., R2LM 2025)
ACL
- Milica Ikonić Nešić, Sasa Petalinkar, Ranka Stanković, and Ruslan Mitkov. 2025. From Zero to Hero: Building Serbian NER from Rules to LLMs. In Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models, pages 87–96, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.