@inproceedings{trusca-etal-2026-contextual,
title = "Contextual Probing for Low-Resource Named Entity Recognition in {L}atin",
author = "Trusca, Maria Mihaela and
Depauw, Mark and
Soen, Violet and
de Daele, Ine and
Verbruggen, Kevin and
Van de Cruys, Tim",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.45/",
doi = "10.63317/4xfc9y3we5j9",
pages = "437--442",
abstract = "Named Entity Recognition (NER) for low-resource languages remains challenging due to limited annotated data and linguistic characteristics such as rich morphology and flexible word order. In this work, we propose a probing-based method that leverages the contextual knowledge encoded in pretrained language models to detect entities. Our approach uses a substitution strategy in which words in a sentence are replaced, one by one, with candidate entities of predefined entity types, referred to as probes. By measuring how well the probes of a certain entity type fit the surrounding context of the replaced word, we estimate the compatibility between the replaced word and the entity type. The resulting compatibility scores can be used either as a standalone zero-shot NER model or as an auxiliary feature during NER model decoding. We evaluate our method on the Latin dataset provided in the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA). Our system ranked second in the coarse-grained NER task. For the fine-grained NER task, where no training data were available, we relied exclusively on the proposed scoring method without any model training and achieved third place. These results demonstrate that contextual probing can provide an effective signal for NER in low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trusca-etal-2026-contextual">
<titleInfo>
<title>Contextual Probing for Low-Resource Named Entity Recognition in Latin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Mihaela</namePart>
<namePart type="family">Trusca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Depauw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Soen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ine</namePart>
<namePart type="family">de Daele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Verbruggen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Van de Cruys</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 Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entity Recognition (NER) for low-resource languages remains challenging due to limited annotated data and linguistic characteristics such as rich morphology and flexible word order. In this work, we propose a probing-based method that leverages the contextual knowledge encoded in pretrained language models to detect entities. Our approach uses a substitution strategy in which words in a sentence are replaced, one by one, with candidate entities of predefined entity types, referred to as probes. By measuring how well the probes of a certain entity type fit the surrounding context of the replaced word, we estimate the compatibility between the replaced word and the entity type. The resulting compatibility scores can be used either as a standalone zero-shot NER model or as an auxiliary feature during NER model decoding. We evaluate our method on the Latin dataset provided in the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA). Our system ranked second in the coarse-grained NER task. For the fine-grained NER task, where no training data were available, we relied exclusively on the proposed scoring method without any model training and achieved third place. These results demonstrate that contextual probing can provide an effective signal for NER in low-resource settings.</abstract>
<identifier type="citekey">trusca-etal-2026-contextual</identifier>
<identifier type="doi">10.63317/4xfc9y3we5j9</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.45/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>437</start>
<end>442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextual Probing for Low-Resource Named Entity Recognition in Latin
%A Trusca, Maria Mihaela
%A Depauw, Mark
%A Soen, Violet
%A de Daele, Ine
%A Verbruggen, Kevin
%A Van de Cruys, Tim
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F trusca-etal-2026-contextual
%X Named Entity Recognition (NER) for low-resource languages remains challenging due to limited annotated data and linguistic characteristics such as rich morphology and flexible word order. In this work, we propose a probing-based method that leverages the contextual knowledge encoded in pretrained language models to detect entities. Our approach uses a substitution strategy in which words in a sentence are replaced, one by one, with candidate entities of predefined entity types, referred to as probes. By measuring how well the probes of a certain entity type fit the surrounding context of the replaced word, we estimate the compatibility between the replaced word and the entity type. The resulting compatibility scores can be used either as a standalone zero-shot NER model or as an auxiliary feature during NER model decoding. We evaluate our method on the Latin dataset provided in the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA). Our system ranked second in the coarse-grained NER task. For the fine-grained NER task, where no training data were available, we relied exclusively on the proposed scoring method without any model training and achieved third place. These results demonstrate that contextual probing can provide an effective signal for NER in low-resource settings.
%R 10.63317/4xfc9y3we5j9
%U https://aclanthology.org/2026.lt4hala-1.45/
%U https://doi.org/10.63317/4xfc9y3we5j9
%P 437-442
Markdown (Informal)
[Contextual Probing for Low-Resource Named Entity Recognition in Latin](https://aclanthology.org/2026.lt4hala-1.45/) (Trusca et al., LT4HALA 2026)
ACL
- Maria Mihaela Trusca, Mark Depauw, Violet Soen, Ine de Daele, Kevin Verbruggen, and Tim Van de Cruys. 2026. Contextual Probing for Low-Resource Named Entity Recognition in Latin. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 437–442, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).