@inproceedings{van-der-lee-van-den-bosch-2017-exploring,
title = "Exploring Lexical and Syntactic Features for Language Variety Identification",
author = "van der Lee, Chris and
van den Bosch, Antal",
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/W17-1224",
doi = "10.18653/v1/W17-1224",
pages = "190--199",
abstract = "We present a method to discriminate between texts written in either the Netherlandic or the Flemish variant of the Dutch language. The method draws on a feature bundle representing text statistics, syntactic features, and word $n$-grams. Text statistics include average word length and sentence length, while syntactic features include ratios of function words and part-of-speech $n$-grams. The effectiveness of the classifier was measured by classifying Dutch subtitles developed for either Dutch or Flemish television. Several machine learning algorithms were compared as well as feature combination methods in order to find the optimal generalization performance. A machine-learning meta classifier based on AdaBoost attained the best F-score of 0.92.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-der-lee-van-den-bosch-2017-exploring">
<titleInfo>
<title>Exploring Lexical and Syntactic Features for Language Variety Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">van der Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antal</namePart>
<namePart type="family">van den Bosch</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>We present a method to discriminate between texts written in either the Netherlandic or the Flemish variant of the Dutch language. The method draws on a feature bundle representing text statistics, syntactic features, and word n-grams. Text statistics include average word length and sentence length, while syntactic features include ratios of function words and part-of-speech n-grams. The effectiveness of the classifier was measured by classifying Dutch subtitles developed for either Dutch or Flemish television. Several machine learning algorithms were compared as well as feature combination methods in order to find the optimal generalization performance. A machine-learning meta classifier based on AdaBoost attained the best F-score of 0.92.</abstract>
<identifier type="citekey">van-der-lee-van-den-bosch-2017-exploring</identifier>
<identifier type="doi">10.18653/v1/W17-1224</identifier>
<location>
<url>https://aclanthology.org/W17-1224</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>190</start>
<end>199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Lexical and Syntactic Features for Language Variety Identification
%A van der Lee, Chris
%A van den Bosch, Antal
%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 van-der-lee-van-den-bosch-2017-exploring
%X We present a method to discriminate between texts written in either the Netherlandic or the Flemish variant of the Dutch language. The method draws on a feature bundle representing text statistics, syntactic features, and word n-grams. Text statistics include average word length and sentence length, while syntactic features include ratios of function words and part-of-speech n-grams. The effectiveness of the classifier was measured by classifying Dutch subtitles developed for either Dutch or Flemish television. Several machine learning algorithms were compared as well as feature combination methods in order to find the optimal generalization performance. A machine-learning meta classifier based on AdaBoost attained the best F-score of 0.92.
%R 10.18653/v1/W17-1224
%U https://aclanthology.org/W17-1224
%U https://doi.org/10.18653/v1/W17-1224
%P 190-199
Markdown (Informal)
[Exploring Lexical and Syntactic Features for Language Variety Identification](https://aclanthology.org/W17-1224) (van der Lee & van den Bosch, VarDial 2017)
ACL