@inproceedings{gamallo-etal-2017-perplexity,
title = "A Perplexity-Based Method for Similar Languages Discrimination",
author = "Gamallo, Pablo and
Pichel, Jose Ramom and
Alegria, I{\~n}aki",
editor = {Nakov, Preslav and
Zampieri, Marcos and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shevin and
Ali, Ahmed},
booktitle = "Proceedings of the Fourth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial)",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1213",
doi = "10.18653/v1/W17-1213",
pages = "109--114",
abstract = "This article describes the system submitted by the Citius{\_}Ixa{\_}Imaxin team to the VarDial 2017 (DSL and GDI tasks). The strategy underlying our system is based on a language distance computed by means of model perplexity. The best model configuration we have tested is a voting system making use of several $n$-grams models of both words and characters, even if word unigrams turned out to be a very competitive model with reasonable results in the tasks we have participated. An error analysis has been performed in which we identified many test examples with no linguistic evidences to distinguish among the variants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gamallo-etal-2017-perplexity">
<titleInfo>
<title>A Perplexity-Based Method for Similar Languages Discrimination</title>
</titleInfo>
<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">Jose</namePart>
<namePart type="given">Ramom</namePart>
<namePart type="family">Pichel</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>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)</title>
</titleInfo>
<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">Marcos</namePart>
<namePart type="family">Zampieri</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">Shevin</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">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the system submitted by the Citius_Ixa_Imaxin team to the VarDial 2017 (DSL and GDI tasks). The strategy underlying our system is based on a language distance computed by means of model perplexity. The best model configuration we have tested is a voting system making use of several n-grams models of both words and characters, even if word unigrams turned out to be a very competitive model with reasonable results in the tasks we have participated. An error analysis has been performed in which we identified many test examples with no linguistic evidences to distinguish among the variants.</abstract>
<identifier type="citekey">gamallo-etal-2017-perplexity</identifier>
<identifier type="doi">10.18653/v1/W17-1213</identifier>
<location>
<url>https://aclanthology.org/W17-1213</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>109</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Perplexity-Based Method for Similar Languages Discrimination
%A Gamallo, Pablo
%A Pichel, Jose Ramom
%A Alegria, Iñaki
%Y Nakov, Preslav
%Y Zampieri, Marcos
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shevin
%Y Ali, Ahmed
%S Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F gamallo-etal-2017-perplexity
%X This article describes the system submitted by the Citius_Ixa_Imaxin team to the VarDial 2017 (DSL and GDI tasks). The strategy underlying our system is based on a language distance computed by means of model perplexity. The best model configuration we have tested is a voting system making use of several n-grams models of both words and characters, even if word unigrams turned out to be a very competitive model with reasonable results in the tasks we have participated. An error analysis has been performed in which we identified many test examples with no linguistic evidences to distinguish among the variants.
%R 10.18653/v1/W17-1213
%U https://aclanthology.org/W17-1213
%U https://doi.org/10.18653/v1/W17-1213
%P 109-114
Markdown (Informal)
[A Perplexity-Based Method for Similar Languages Discrimination](https://aclanthology.org/W17-1213) (Gamallo et al., VarDial 2017)
ACL