@inproceedings{pichel-campos-etal-2018-measuring,
title = "Measuring language distance among historical varieties using perplexity. Application to {E}uropean {P}ortuguese.",
author = "Pichel Campos, Jose Ramom and
Gamallo, Pablo and
Alegria, I{\~n}aki",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin and
Ali, Ahmed},
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial 2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3916",
pages = "145--155",
abstract = "The objective of this work is to quantify, with a simple and robust measure, the distance between historical varieties of a language. The measure will be inferred from text corpora corresponding to historical periods. Different approaches have been proposed for similar aims: Language Identification, Phylogenetics, Historical Linguistics or Dialectology. In our approach, we used a perplexity-based measure to calculate language distance between all the historical periods of a specific language: European Portuguese. Perplexity has also proven to be a robust metric to calculate distance between languages. However, this measure has not been tested yet to identify diachronic periods within the historical evolution of a specific language. For this purpose, a historical Portuguese corpus has been constructed from different open sources containing texts with close original spelling. The results of our experiments show that Portuguese keeps an important degree of homogeneity over time. We anticipate this metric to be a starting point to be applied to other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pichel-campos-etal-2018-measuring">
<titleInfo>
<title>Measuring language distance among historical varieties using perplexity. Application to European Portuguese.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">Ramom</namePart>
<namePart type="family">Pichel Campos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gamallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñaki</namePart>
<namePart type="family">Alegria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The objective of this work is to quantify, with a simple and robust measure, the distance between historical varieties of a language. The measure will be inferred from text corpora corresponding to historical periods. Different approaches have been proposed for similar aims: Language Identification, Phylogenetics, Historical Linguistics or Dialectology. In our approach, we used a perplexity-based measure to calculate language distance between all the historical periods of a specific language: European Portuguese. Perplexity has also proven to be a robust metric to calculate distance between languages. However, this measure has not been tested yet to identify diachronic periods within the historical evolution of a specific language. For this purpose, a historical Portuguese corpus has been constructed from different open sources containing texts with close original spelling. The results of our experiments show that Portuguese keeps an important degree of homogeneity over time. We anticipate this metric to be a starting point to be applied to other languages.</abstract>
<identifier type="citekey">pichel-campos-etal-2018-measuring</identifier>
<location>
<url>https://aclanthology.org/W18-3916</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>145</start>
<end>155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring language distance among historical varieties using perplexity. Application to European Portuguese.
%A Pichel Campos, Jose Ramom
%A Gamallo, Pablo
%A Alegria, Iñaki
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%Y Ali, Ahmed
%S Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F pichel-campos-etal-2018-measuring
%X The objective of this work is to quantify, with a simple and robust measure, the distance between historical varieties of a language. The measure will be inferred from text corpora corresponding to historical periods. Different approaches have been proposed for similar aims: Language Identification, Phylogenetics, Historical Linguistics or Dialectology. In our approach, we used a perplexity-based measure to calculate language distance between all the historical periods of a specific language: European Portuguese. Perplexity has also proven to be a robust metric to calculate distance between languages. However, this measure has not been tested yet to identify diachronic periods within the historical evolution of a specific language. For this purpose, a historical Portuguese corpus has been constructed from different open sources containing texts with close original spelling. The results of our experiments show that Portuguese keeps an important degree of homogeneity over time. We anticipate this metric to be a starting point to be applied to other languages.
%U https://aclanthology.org/W18-3916
%P 145-155
Markdown (Informal)
[Measuring language distance among historical varieties using perplexity. Application to European Portuguese.](https://aclanthology.org/W18-3916) (Pichel Campos et al., VarDial 2018)
ACL