@inproceedings{goutte-leger-2016-advances,
title = "Advances in Ngram-based Discrimination of Similar Languages",
author = "Goutte, Cyril and
L{\'e}ger, Serge",
editor = {Nakov, Preslav and
Zampieri, Marcos and
Tan, Liling and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin},
booktitle = "Proceedings of the Third Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial3)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4823",
pages = "178--184",
abstract = "We describe the systems entered by the National Research Council in the 2016 shared task on discriminating similar languages. Like previous years, we relied on character ngram features, and a mixture of discriminative and generative statistical classifiers. We mostly investigated the influence of the amount of data on the performance, in the open task, and compared the two-stage approach (predicting language/group, then variant) to a flat approach. Results suggest that ngrams are still state-of-the-art for language and variant identification, and that additional data has a small but decisive impact.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goutte-leger-2016-advances">
<titleInfo>
<title>Advances in Ngram-based Discrimination of Similar Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Goutte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Léger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)</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">Liling</namePart>
<namePart type="family">Tan</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>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe the systems entered by the National Research Council in the 2016 shared task on discriminating similar languages. Like previous years, we relied on character ngram features, and a mixture of discriminative and generative statistical classifiers. We mostly investigated the influence of the amount of data on the performance, in the open task, and compared the two-stage approach (predicting language/group, then variant) to a flat approach. Results suggest that ngrams are still state-of-the-art for language and variant identification, and that additional data has a small but decisive impact.</abstract>
<identifier type="citekey">goutte-leger-2016-advances</identifier>
<location>
<url>https://aclanthology.org/W16-4823</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>178</start>
<end>184</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advances in Ngram-based Discrimination of Similar Languages
%A Goutte, Cyril
%A Léger, Serge
%Y Nakov, Preslav
%Y Zampieri, Marcos
%Y Tan, Liling
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%S Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F goutte-leger-2016-advances
%X We describe the systems entered by the National Research Council in the 2016 shared task on discriminating similar languages. Like previous years, we relied on character ngram features, and a mixture of discriminative and generative statistical classifiers. We mostly investigated the influence of the amount of data on the performance, in the open task, and compared the two-stage approach (predicting language/group, then variant) to a flat approach. Results suggest that ngrams are still state-of-the-art for language and variant identification, and that additional data has a small but decisive impact.
%U https://aclanthology.org/W16-4823
%P 178-184
Markdown (Informal)
[Advances in Ngram-based Discrimination of Similar Languages](https://aclanthology.org/W16-4823) (Goutte & Léger, VarDial 2016)
ACL