@inproceedings{alatrush-etal-2025-advancing,
title = "Advancing Active Learning with Ensemble Strategies",
author = "Alatrush, Naif and
Alsarra, Sultan and
Alshammari, Afraa and
Abdeljaber, Luay and
Zawad, Niamat and
Khan, Latifur and
Brandt, Patrick T. and
Osorio, Javier and
D{'}Orazio, Vito",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.7/",
pages = "57--66",
abstract = "Active learning (AL) reduces annotation costs by selecting the most informative samples for labeling. However, traditional AL methods rely on a single heuristic, limiting data exploration and annotation efficiency. This paper introduces two ensemble-based AL methods: Ensemble Union, which combines multiple heuristics to improve dataset exploration, and Ensemble Intersection, which applies majority voting for robust sample selection. We evaluate these approaches on the United Nations Parallel Corpus (UNPC) in both English and Spanish using domain-specific models such as ConfliBERT. Our results show that ensemble-based AL strategies outperform individual heuristics, achieving classification performance comparable to full dataset training while using significantly fewer labeled examples. Although focused on political texts, the proposed methods are applicable to broader NLP annotation tasks where labeling costs are high."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alatrush-etal-2025-advancing">
<titleInfo>
<title>Advancing Active Learning with Ensemble Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naif</namePart>
<namePart type="family">Alatrush</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sultan</namePart>
<namePart type="family">Alsarra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afraa</namePart>
<namePart type="family">Alshammari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luay</namePart>
<namePart type="family">Abdeljaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niamat</namePart>
<namePart type="family">Zawad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Latifur</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Brandt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Osorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vito</namePart>
<namePart type="family">D’Orazio</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 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</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>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Active learning (AL) reduces annotation costs by selecting the most informative samples for labeling. However, traditional AL methods rely on a single heuristic, limiting data exploration and annotation efficiency. This paper introduces two ensemble-based AL methods: Ensemble Union, which combines multiple heuristics to improve dataset exploration, and Ensemble Intersection, which applies majority voting for robust sample selection. We evaluate these approaches on the United Nations Parallel Corpus (UNPC) in both English and Spanish using domain-specific models such as ConfliBERT. Our results show that ensemble-based AL strategies outperform individual heuristics, achieving classification performance comparable to full dataset training while using significantly fewer labeled examples. Although focused on political texts, the proposed methods are applicable to broader NLP annotation tasks where labeling costs are high.</abstract>
<identifier type="citekey">alatrush-etal-2025-advancing</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.7/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>57</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advancing Active Learning with Ensemble Strategies
%A Alatrush, Naif
%A Alsarra, Sultan
%A Alshammari, Afraa
%A Abdeljaber, Luay
%A Zawad, Niamat
%A Khan, Latifur
%A Brandt, Patrick T.
%A Osorio, Javier
%A D’Orazio, Vito
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F alatrush-etal-2025-advancing
%X Active learning (AL) reduces annotation costs by selecting the most informative samples for labeling. However, traditional AL methods rely on a single heuristic, limiting data exploration and annotation efficiency. This paper introduces two ensemble-based AL methods: Ensemble Union, which combines multiple heuristics to improve dataset exploration, and Ensemble Intersection, which applies majority voting for robust sample selection. We evaluate these approaches on the United Nations Parallel Corpus (UNPC) in both English and Spanish using domain-specific models such as ConfliBERT. Our results show that ensemble-based AL strategies outperform individual heuristics, achieving classification performance comparable to full dataset training while using significantly fewer labeled examples. Although focused on political texts, the proposed methods are applicable to broader NLP annotation tasks where labeling costs are high.
%U https://aclanthology.org/2025.ranlp-1.7/
%P 57-66
Markdown (Informal)
[Advancing Active Learning with Ensemble Strategies](https://aclanthology.org/2025.ranlp-1.7/) (Alatrush et al., RANLP 2025)
ACL
- Naif Alatrush, Sultan Alsarra, Afraa Alshammari, Luay Abdeljaber, Niamat Zawad, Latifur Khan, Patrick T. Brandt, Javier Osorio, and Vito D’Orazio. 2025. Advancing Active Learning with Ensemble Strategies. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 57–66, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.