@inproceedings{bloem-etal-2020-distributional,
title = "Distributional Semantics for Neo-{L}atin",
author = "Bloem, Jelke and
Parisi, Maria Chiara and
Reynaert, Martin and
Oortwijn, Yvette and
Betti, Arianna",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.lt4hala-1.13",
pages = "84--93",
abstract = "We address the problem of creating and evaluating quality Neo-Latin word embeddings for the purpose of philosophical research, adapting the Nonce2Vec tool to learn embeddings from Neo-Latin sentences. This distributional semantic modeling tool can learn from tiny data incrementally, using a larger background corpus for initialization. We conduct two evaluation tasks: definitional learning of Latin Wikipedia terms, and learning consistent embeddings from 18th century Neo-Latin sentences pertaining to the concept of mathematical method. Our results show that consistent Neo-Latin word embeddings can be learned from this type of data. While our evaluation results are promising, they do not reveal to what extent the learned models match domain expert knowledge of our Neo-Latin texts. Therefore, we propose an additional evaluation method, grounded in expert-annotated data, that would assess whether learned representations are conceptually sound in relation to the domain of study.",
language = "English",
ISBN = "979-10-95546-53-5",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bloem-etal-2020-distributional">
<titleInfo>
<title>Distributional Semantics for Neo-Latin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jelke</namePart>
<namePart type="family">Bloem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Chiara</namePart>
<namePart type="family">Parisi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Reynaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Oortwijn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Betti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages</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>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-53-5</identifier>
</relatedItem>
<abstract>We address the problem of creating and evaluating quality Neo-Latin word embeddings for the purpose of philosophical research, adapting the Nonce2Vec tool to learn embeddings from Neo-Latin sentences. This distributional semantic modeling tool can learn from tiny data incrementally, using a larger background corpus for initialization. We conduct two evaluation tasks: definitional learning of Latin Wikipedia terms, and learning consistent embeddings from 18th century Neo-Latin sentences pertaining to the concept of mathematical method. Our results show that consistent Neo-Latin word embeddings can be learned from this type of data. While our evaluation results are promising, they do not reveal to what extent the learned models match domain expert knowledge of our Neo-Latin texts. Therefore, we propose an additional evaluation method, grounded in expert-annotated data, that would assess whether learned representations are conceptually sound in relation to the domain of study.</abstract>
<identifier type="citekey">bloem-etal-2020-distributional</identifier>
<location>
<url>https://aclanthology.org/2020.lt4hala-1.13</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>84</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distributional Semantics for Neo-Latin
%A Bloem, Jelke
%A Parisi, Maria Chiara
%A Reynaert, Martin
%A Oortwijn, Yvette
%A Betti, Arianna
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-53-5
%G English
%F bloem-etal-2020-distributional
%X We address the problem of creating and evaluating quality Neo-Latin word embeddings for the purpose of philosophical research, adapting the Nonce2Vec tool to learn embeddings from Neo-Latin sentences. This distributional semantic modeling tool can learn from tiny data incrementally, using a larger background corpus for initialization. We conduct two evaluation tasks: definitional learning of Latin Wikipedia terms, and learning consistent embeddings from 18th century Neo-Latin sentences pertaining to the concept of mathematical method. Our results show that consistent Neo-Latin word embeddings can be learned from this type of data. While our evaluation results are promising, they do not reveal to what extent the learned models match domain expert knowledge of our Neo-Latin texts. Therefore, we propose an additional evaluation method, grounded in expert-annotated data, that would assess whether learned representations are conceptually sound in relation to the domain of study.
%U https://aclanthology.org/2020.lt4hala-1.13
%P 84-93
Markdown (Informal)
[Distributional Semantics for Neo-Latin](https://aclanthology.org/2020.lt4hala-1.13) (Bloem et al., LT4HALA 2020)
ACL
- Jelke Bloem, Maria Chiara Parisi, Martin Reynaert, Yvette Oortwijn, and Arianna Betti. 2020. Distributional Semantics for Neo-Latin. In Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages, pages 84–93, Marseille, France. European Language Resources Association (ELRA).