@inproceedings{herman-etal-2016-dsl,
title = "{DSL} Shared Task 2016: Perfect Is The Enemy of Good Language Discrimination Through Expectation{--}Maximization and Chunk-based Language Model",
author = "Herman, Ond{\v{r}}ej and
Suchomel, V{\'\i}t and
Baisa, V{\'\i}t and
Rychl{\'y}, Pavel",
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/W16-4815",
pages = "114--118",
abstract = "In this paper we investigate two approaches to discrimination of similar languages: Expectation{--}maximization algorithm for estimating conditional probability P(word|language) and byte level language models similar to compression-based language modelling methods. The accuracy of these methods reached respectively 86.6{\%} and 88.3{\%} on set A of the DSL Shared task 2016 competition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="herman-etal-2016-dsl">
<titleInfo>
<title>DSL Shared Task 2016: Perfect Is The Enemy of Good Language Discrimination Through Expectation–Maximization and Chunk-based Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Herman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vít</namePart>
<namePart type="family">Suchomel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vít</namePart>
<namePart type="family">Baisa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Rychlý</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>In this paper we investigate two approaches to discrimination of similar languages: Expectation–maximization algorithm for estimating conditional probability P(word|language) and byte level language models similar to compression-based language modelling methods. The accuracy of these methods reached respectively 86.6% and 88.3% on set A of the DSL Shared task 2016 competition.</abstract>
<identifier type="citekey">herman-etal-2016-dsl</identifier>
<location>
<url>https://aclanthology.org/W16-4815</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>114</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DSL Shared Task 2016: Perfect Is The Enemy of Good Language Discrimination Through Expectation–Maximization and Chunk-based Language Model
%A Herman, Ondřej
%A Suchomel, Vít
%A Baisa, Vít
%A Rychlý, Pavel
%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 herman-etal-2016-dsl
%X In this paper we investigate two approaches to discrimination of similar languages: Expectation–maximization algorithm for estimating conditional probability P(word|language) and byte level language models similar to compression-based language modelling methods. The accuracy of these methods reached respectively 86.6% and 88.3% on set A of the DSL Shared task 2016 competition.
%U https://aclanthology.org/W16-4815
%P 114-118
Markdown (Informal)
[DSL Shared Task 2016: Perfect Is The Enemy of Good Language Discrimination Through Expectation–Maximization and Chunk-based Language Model](https://aclanthology.org/W16-4815) (Herman et al., VarDial 2016)
ACL