@inproceedings{van-zaanen-etal-2014-development,
title = "The Development of {D}utch and {A}frikaans Language Resources for Compound Boundary Analysis.",
author = "van Zaanen, Menno and
van Huyssteen, Gerhard and
Aussems, Suzanne and
Emmery, Chris and
Eiselen, Roald",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/66_Paper.pdf",
pages = "1056--1062",
abstract = "In most languages, new words can be created through the process of compounding, which combines two or more words into a new lexical unit. Whereas in languages such as English the components that make up a compound are separated by a space, in languages such as Finnish, German, Afrikaans and Dutch these components are concatenated into one word. Compounding is very productive and leads to practical problems in developing machine translators and spelling checkers, as newly formed compounds cannot be found in existing lexicons. The Automatic Compound Processing (AuCoPro) project deals with the analysis of compounds in two closely-related languages, Afrikaans and Dutch. In this paper, we present the development and evaluation of two datasets, one for each language, that contain compound words with annotated compound boundaries. Such datasets can be used to train classifiers to identify the compound components in novel compounds. We describe the process of annotation and provide an overview of the annotation guidelines as well as global properties of the datasets. The inter-rater agreements between the annotators are considered highly reliable. Furthermore, we show the usability of these datasets by building an initial automatic compound boundary detection system, which assigns compound boundaries with approximately 90{\%} accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-zaanen-etal-2014-development">
<titleInfo>
<title>The Development of Dutch and Afrikaans Language Resources for Compound Boundary Analysis.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerhard</namePart>
<namePart type="family">van Huyssteen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzanne</namePart>
<namePart type="family">Aussems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Emmery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roald</namePart>
<namePart type="family">Eiselen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In most languages, new words can be created through the process of compounding, which combines two or more words into a new lexical unit. Whereas in languages such as English the components that make up a compound are separated by a space, in languages such as Finnish, German, Afrikaans and Dutch these components are concatenated into one word. Compounding is very productive and leads to practical problems in developing machine translators and spelling checkers, as newly formed compounds cannot be found in existing lexicons. The Automatic Compound Processing (AuCoPro) project deals with the analysis of compounds in two closely-related languages, Afrikaans and Dutch. In this paper, we present the development and evaluation of two datasets, one for each language, that contain compound words with annotated compound boundaries. Such datasets can be used to train classifiers to identify the compound components in novel compounds. We describe the process of annotation and provide an overview of the annotation guidelines as well as global properties of the datasets. The inter-rater agreements between the annotators are considered highly reliable. Furthermore, we show the usability of these datasets by building an initial automatic compound boundary detection system, which assigns compound boundaries with approximately 90% accuracy.</abstract>
<identifier type="citekey">van-zaanen-etal-2014-development</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/66_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1056</start>
<end>1062</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Development of Dutch and Afrikaans Language Resources for Compound Boundary Analysis.
%A van Zaanen, Menno
%A van Huyssteen, Gerhard
%A Aussems, Suzanne
%A Emmery, Chris
%A Eiselen, Roald
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F van-zaanen-etal-2014-development
%X In most languages, new words can be created through the process of compounding, which combines two or more words into a new lexical unit. Whereas in languages such as English the components that make up a compound are separated by a space, in languages such as Finnish, German, Afrikaans and Dutch these components are concatenated into one word. Compounding is very productive and leads to practical problems in developing machine translators and spelling checkers, as newly formed compounds cannot be found in existing lexicons. The Automatic Compound Processing (AuCoPro) project deals with the analysis of compounds in two closely-related languages, Afrikaans and Dutch. In this paper, we present the development and evaluation of two datasets, one for each language, that contain compound words with annotated compound boundaries. Such datasets can be used to train classifiers to identify the compound components in novel compounds. We describe the process of annotation and provide an overview of the annotation guidelines as well as global properties of the datasets. The inter-rater agreements between the annotators are considered highly reliable. Furthermore, we show the usability of these datasets by building an initial automatic compound boundary detection system, which assigns compound boundaries with approximately 90% accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/66_Paper.pdf
%P 1056-1062
Markdown (Informal)
[The Development of Dutch and Afrikaans Language Resources for Compound Boundary Analysis.](http://www.lrec-conf.org/proceedings/lrec2014/pdf/66_Paper.pdf) (van Zaanen et al., LREC 2014)
ACL