@inproceedings{ripoll-alberola-etal-2026-classificatio,
title = "Classificatio Sine Iactu {--} That Is, Zero-Shot {NERC} in {L}atin",
author = "Ripoll-Alberola, Luisa and
Nicol{\'a}s-Flores, Fernando and
Mu{\~n}oz Acebes, Francisco Javier",
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-1.46/",
doi = "10.63317/4zrvjjxzw5yr",
pages = "443--447",
abstract = "This paper presents a zero-shot approach to Named-Entity Recognition and Classification (NERC) in Latin, applied to the EvaLatin shared task. Given the novelty and granularity of the annotation guidelines, which preclude the use of existing annotated resources, we employ the zero-shot model GLiNER2, a general information extraction system capable of CPU-efficient inference, within a cross-lingual pipeline. Latin texts are first translated into English via the Google Translate API, processed by the model, and the resulting annotations are aligned back to the original Latin using word-alignment techniques. Rule-based post-processing addresses labelling inconsistencies and low-confidence predictions. We evaluate two model variants, a large monolingual and a multilingual model, under both strict and fuzzy evaluation. The large model delivers the best results for the coarse-grained task (F1: 0.590 fuzzy), while the multilingual model outperforms it on the fine-grained task (F1: 0.432 fuzzy). Results indicate that multilingual embeddings confer an advantage for fine-grained semantic distinctions, that English embeddings introduce systematic bias in cross-lingual transfer, and that zero-shot NER represents a viable, reproducible baseline for low-resource historical languages. Fine-tuning on guideline-compliant annotated data remains a priority for future work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ripoll-alberola-etal-2026-classificatio">
<titleInfo>
<title>Classificatio Sine Iactu – That Is, Zero-Shot NERC in Latin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Ripoll-Alberola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Nicolás-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="given">Javier</namePart>
<namePart type="family">Muñoz Acebes</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>This paper presents a zero-shot approach to Named-Entity Recognition and Classification (NERC) in Latin, applied to the EvaLatin shared task. Given the novelty and granularity of the annotation guidelines, which preclude the use of existing annotated resources, we employ the zero-shot model GLiNER2, a general information extraction system capable of CPU-efficient inference, within a cross-lingual pipeline. Latin texts are first translated into English via the Google Translate API, processed by the model, and the resulting annotations are aligned back to the original Latin using word-alignment techniques. Rule-based post-processing addresses labelling inconsistencies and low-confidence predictions. We evaluate two model variants, a large monolingual and a multilingual model, under both strict and fuzzy evaluation. The large model delivers the best results for the coarse-grained task (F1: 0.590 fuzzy), while the multilingual model outperforms it on the fine-grained task (F1: 0.432 fuzzy). Results indicate that multilingual embeddings confer an advantage for fine-grained semantic distinctions, that English embeddings introduce systematic bias in cross-lingual transfer, and that zero-shot NER represents a viable, reproducible baseline for low-resource historical languages. Fine-tuning on guideline-compliant annotated data remains a priority for future work.</abstract>
<identifier type="citekey">ripoll-alberola-etal-2026-classificatio</identifier>
<identifier type="doi">10.63317/4zrvjjxzw5yr</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.46/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>443</start>
<end>447</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Classificatio Sine Iactu – That Is, Zero-Shot NERC in Latin
%A Ripoll-Alberola, Luisa
%A Nicolás-Flores, Fernando
%A Muñoz Acebes, Francisco Javier
%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 ripoll-alberola-etal-2026-classificatio
%X This paper presents a zero-shot approach to Named-Entity Recognition and Classification (NERC) in Latin, applied to the EvaLatin shared task. Given the novelty and granularity of the annotation guidelines, which preclude the use of existing annotated resources, we employ the zero-shot model GLiNER2, a general information extraction system capable of CPU-efficient inference, within a cross-lingual pipeline. Latin texts are first translated into English via the Google Translate API, processed by the model, and the resulting annotations are aligned back to the original Latin using word-alignment techniques. Rule-based post-processing addresses labelling inconsistencies and low-confidence predictions. We evaluate two model variants, a large monolingual and a multilingual model, under both strict and fuzzy evaluation. The large model delivers the best results for the coarse-grained task (F1: 0.590 fuzzy), while the multilingual model outperforms it on the fine-grained task (F1: 0.432 fuzzy). Results indicate that multilingual embeddings confer an advantage for fine-grained semantic distinctions, that English embeddings introduce systematic bias in cross-lingual transfer, and that zero-shot NER represents a viable, reproducible baseline for low-resource historical languages. Fine-tuning on guideline-compliant annotated data remains a priority for future work.
%R 10.63317/4zrvjjxzw5yr
%U https://aclanthology.org/2026.lt4hala-1.46/
%U https://doi.org/10.63317/4zrvjjxzw5yr
%P 443-447
Markdown (Informal)
[Classificatio Sine Iactu – That Is, Zero-Shot NERC in Latin](https://aclanthology.org/2026.lt4hala-1.46/) (Ripoll-Alberola et al., LT4HALA 2026)
ACL
- Luisa Ripoll-Alberola, Fernando Nicolás-Flores, and Francisco Javier Muñoz Acebes. 2026. Classificatio Sine Iactu – That Is, Zero-Shot NERC in Latin. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 443–447, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).