@inproceedings{bassani-etal-2024-lime,
title = "{L}i{M}e: A {L}atin Corpus of Late Medieval Criminal Sentences",
author = "Bassani, Alessanda Clara Carmela and
Del Bo, Beatrice Giovanna Maria and
Ferrara, Alfio and
Mangini, Marta Luigina and
Picascia, Sergio and
Stefanello, Ambra",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lt4hala-1.6",
pages = "41--49",
abstract = "The Latin language has received attention from the computational linguistics research community, which has built, over the years, several valuable resources, ranging from detailed annotated corpora to sophisticated tools for linguistic analysis. With the recent advent of large language models, researchers have also started developing models capable of generating vector representations of Latin texts. The performances of such models remain behind the ones for modern languages, given the disparity in available data. In this paper, we present the LiMe dataset, a corpus of 325 documents extracted from a series of medieval manuscripts called Libri sententiarum potestatis Mediolani, and thoroughly annotated by experts, in order to be employed for masked language model, as well as supervised natural language processing tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bassani-etal-2024-lime">
<titleInfo>
<title>LiMe: A Latin Corpus of Late Medieval Criminal Sentences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessanda</namePart>
<namePart type="given">Clara</namePart>
<namePart type="given">Carmela</namePart>
<namePart type="family">Bassani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="given">Giovanna</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Del Bo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfio</namePart>
<namePart type="family">Ferrara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">Luigina</namePart>
<namePart type="family">Mangini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Picascia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ambra</namePart>
<namePart type="family">Stefanello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024</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 and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Latin language has received attention from the computational linguistics research community, which has built, over the years, several valuable resources, ranging from detailed annotated corpora to sophisticated tools for linguistic analysis. With the recent advent of large language models, researchers have also started developing models capable of generating vector representations of Latin texts. The performances of such models remain behind the ones for modern languages, given the disparity in available data. In this paper, we present the LiMe dataset, a corpus of 325 documents extracted from a series of medieval manuscripts called Libri sententiarum potestatis Mediolani, and thoroughly annotated by experts, in order to be employed for masked language model, as well as supervised natural language processing tasks.</abstract>
<identifier type="citekey">bassani-etal-2024-lime</identifier>
<location>
<url>https://aclanthology.org/2024.lt4hala-1.6</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>41</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LiMe: A Latin Corpus of Late Medieval Criminal Sentences
%A Bassani, Alessanda Clara Carmela
%A Del Bo, Beatrice Giovanna Maria
%A Ferrara, Alfio
%A Mangini, Marta Luigina
%A Picascia, Sergio
%A Stefanello, Ambra
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bassani-etal-2024-lime
%X The Latin language has received attention from the computational linguistics research community, which has built, over the years, several valuable resources, ranging from detailed annotated corpora to sophisticated tools for linguistic analysis. With the recent advent of large language models, researchers have also started developing models capable of generating vector representations of Latin texts. The performances of such models remain behind the ones for modern languages, given the disparity in available data. In this paper, we present the LiMe dataset, a corpus of 325 documents extracted from a series of medieval manuscripts called Libri sententiarum potestatis Mediolani, and thoroughly annotated by experts, in order to be employed for masked language model, as well as supervised natural language processing tasks.
%U https://aclanthology.org/2024.lt4hala-1.6
%P 41-49
Markdown (Informal)
[LiMe: A Latin Corpus of Late Medieval Criminal Sentences](https://aclanthology.org/2024.lt4hala-1.6) (Bassani et al., LT4HALA-WS 2024)
ACL
- Alessanda Clara Carmela Bassani, Beatrice Giovanna Maria Del Bo, Alfio Ferrara, Marta Luigina Mangini, Sergio Picascia, and Ambra Stefanello. 2024. LiMe: A Latin Corpus of Late Medieval Criminal Sentences. In Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024, pages 41–49, Torino, Italia. ELRA and ICCL.