@inproceedings{hellwig-2020-dating,
title = "Dating and Stratifying a Historical Corpus with a {B}ayesian Mixture Model",
author = "Hellwig, Oliver",
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-1.1",
pages = "1--9",
abstract = "This paper introduces and evaluates a Bayesian mixture model that is designed for dating texts based on the distributions of linguistic features. The model is applied to the corpus of Vedic Sanskrit the historical structure of which is still unclear in many details. The evaluation concentrates on the interaction between time, genre and linguistic features, detecting those whose distributions are clearly coupled with the historical time. The evaluation also highlights the problems that arise when quantitative results need to be reconciled with philological insights.",
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="hellwig-2020-dating">
<titleInfo>
<title>Dating and Stratifying a Historical Corpus with a Bayesian Mixture Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Hellwig</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>This paper introduces and evaluates a Bayesian mixture model that is designed for dating texts based on the distributions of linguistic features. The model is applied to the corpus of Vedic Sanskrit the historical structure of which is still unclear in many details. The evaluation concentrates on the interaction between time, genre and linguistic features, detecting those whose distributions are clearly coupled with the historical time. The evaluation also highlights the problems that arise when quantitative results need to be reconciled with philological insights.</abstract>
<identifier type="citekey">hellwig-2020-dating</identifier>
<location>
<url>https://aclanthology.org/2020.lt4hala-1.1</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dating and Stratifying a Historical Corpus with a Bayesian Mixture Model
%A Hellwig, Oliver
%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 hellwig-2020-dating
%X This paper introduces and evaluates a Bayesian mixture model that is designed for dating texts based on the distributions of linguistic features. The model is applied to the corpus of Vedic Sanskrit the historical structure of which is still unclear in many details. The evaluation concentrates on the interaction between time, genre and linguistic features, detecting those whose distributions are clearly coupled with the historical time. The evaluation also highlights the problems that arise when quantitative results need to be reconciled with philological insights.
%U https://aclanthology.org/2020.lt4hala-1.1
%P 1-9
Markdown (Informal)
[Dating and Stratifying a Historical Corpus with a Bayesian Mixture Model](https://aclanthology.org/2020.lt4hala-1.1) (Hellwig, LT4HALA 2020)
ACL