@inproceedings{marini-etal-2026-extracting,
title = "Extracting Volcanological Knowledge from Historical Texts: A Language-Technology Pipeline for Diachronic Geovisualization",
author = "Marini, Costanza and
Casagrande, Gianluca and
Palmero Aprosio, Alessio and
Principe, Claudia",
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-1.4/",
doi = "10.63317/3ikuq72uxg2t",
pages = "38--48",
abstract = "This paper presents the first results of the CorVo project, a transdisciplinary project combining volcanology and computational linguistics to extract and structure volcanological knowledge from historical documents concerning Mount Vesuvius. We introduce the CorVo corpus, a multilingual diachronic corpus of 180 digitized texts (16th{--}20th centuries), selected to represent the main eruptive scenarios of the volcano. The digitization workflow integrates image pre-processing, OCR, and LLM-based post-correction to address challenges posed by degraded pages, historical typefaces, and orthographic variation. A domain-aware information extraction pipeline was developed to identify both standard toponyms and fine-grained spatial entities, which are typically overlooked by traditional NER systems. Extracted entities undergo human-in-the-loop validation and georeferencing through a dedicated annotation interface supporting multiple spatial geometries. The resulting dataset enables temporally normalized diachronic geovisualization of the textual-spatial footprint of Vesuvian eruptions across centuries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marini-etal-2026-extracting">
<titleInfo>
<title>Extracting Volcanological Knowledge from Historical Texts: A Language-Technology Pipeline for Diachronic Geovisualization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Costanza</namePart>
<namePart type="family">Marini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gianluca</namePart>
<namePart type="family">Casagrande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Palmero Aprosio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Principe</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 the first results of the CorVo project, a transdisciplinary project combining volcanology and computational linguistics to extract and structure volcanological knowledge from historical documents concerning Mount Vesuvius. We introduce the CorVo corpus, a multilingual diachronic corpus of 180 digitized texts (16th–20th centuries), selected to represent the main eruptive scenarios of the volcano. The digitization workflow integrates image pre-processing, OCR, and LLM-based post-correction to address challenges posed by degraded pages, historical typefaces, and orthographic variation. A domain-aware information extraction pipeline was developed to identify both standard toponyms and fine-grained spatial entities, which are typically overlooked by traditional NER systems. Extracted entities undergo human-in-the-loop validation and georeferencing through a dedicated annotation interface supporting multiple spatial geometries. The resulting dataset enables temporally normalized diachronic geovisualization of the textual-spatial footprint of Vesuvian eruptions across centuries.</abstract>
<identifier type="citekey">marini-etal-2026-extracting</identifier>
<identifier type="doi">10.63317/3ikuq72uxg2t</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.4/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>38</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting Volcanological Knowledge from Historical Texts: A Language-Technology Pipeline for Diachronic Geovisualization
%A Marini, Costanza
%A Casagrande, Gianluca
%A Palmero Aprosio, Alessio
%A Principe, Claudia
%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 marini-etal-2026-extracting
%X This paper presents the first results of the CorVo project, a transdisciplinary project combining volcanology and computational linguistics to extract and structure volcanological knowledge from historical documents concerning Mount Vesuvius. We introduce the CorVo corpus, a multilingual diachronic corpus of 180 digitized texts (16th–20th centuries), selected to represent the main eruptive scenarios of the volcano. The digitization workflow integrates image pre-processing, OCR, and LLM-based post-correction to address challenges posed by degraded pages, historical typefaces, and orthographic variation. A domain-aware information extraction pipeline was developed to identify both standard toponyms and fine-grained spatial entities, which are typically overlooked by traditional NER systems. Extracted entities undergo human-in-the-loop validation and georeferencing through a dedicated annotation interface supporting multiple spatial geometries. The resulting dataset enables temporally normalized diachronic geovisualization of the textual-spatial footprint of Vesuvian eruptions across centuries.
%R 10.63317/3ikuq72uxg2t
%U https://aclanthology.org/2026.lt4hala-1.4/
%U https://doi.org/10.63317/3ikuq72uxg2t
%P 38-48
Markdown (Informal)
[Extracting Volcanological Knowledge from Historical Texts: A Language-Technology Pipeline for Diachronic Geovisualization](https://aclanthology.org/2026.lt4hala-1.4/) (Marini et al., LT4HALA 2026)
ACL