@inproceedings{steiner-2016-refurbishing,
title = "Refurbishing a Morphological Database for {G}erman",
author = "Steiner, Petra",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1176",
pages = "1103--1108",
abstract = "The CELEX database is one of the standard lexical resources for German. It yields a wealth of data especially for phonological and morphological applications. The morphological part comprises deep-structure morphological analyses of German. However, as it was developed in the Nineties, both encoding and spelling are outdated. About one fifth of over 50,000 datasets contain umlauts and signs such as {\ss}. Changes to a modern version cannot be obtained by simple substitution. In this paper, we shortly describe the original content and form of the orthographic and morphological database for German in CELEX. Then we present our work on modernizing the linguistic data. Lemmas and morphological analyses are transferred to a modern standard of encoding by first merging orthographic and morphological information of the lemmas and their entries and then performing a second substitution for the morphs within their morphological analyses. Changes to modern German spelling are performed by substitution rules according to orthographical standards. We show an example of the use of the data for the disambiguation of morphological structures. The discussion describes prospects of future work on this or similar lexicons. The Perl script is publicly available on our website.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="steiner-2016-refurbishing">
<titleInfo>
<title>Refurbishing a Morphological Database for German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Petra</namePart>
<namePart type="family">Steiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The CELEX database is one of the standard lexical resources for German. It yields a wealth of data especially for phonological and morphological applications. The morphological part comprises deep-structure morphological analyses of German. However, as it was developed in the Nineties, both encoding and spelling are outdated. About one fifth of over 50,000 datasets contain umlauts and signs such as ß. Changes to a modern version cannot be obtained by simple substitution. In this paper, we shortly describe the original content and form of the orthographic and morphological database for German in CELEX. Then we present our work on modernizing the linguistic data. Lemmas and morphological analyses are transferred to a modern standard of encoding by first merging orthographic and morphological information of the lemmas and their entries and then performing a second substitution for the morphs within their morphological analyses. Changes to modern German spelling are performed by substitution rules according to orthographical standards. We show an example of the use of the data for the disambiguation of morphological structures. The discussion describes prospects of future work on this or similar lexicons. The Perl script is publicly available on our website.</abstract>
<identifier type="citekey">steiner-2016-refurbishing</identifier>
<location>
<url>https://aclanthology.org/L16-1176</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1103</start>
<end>1108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refurbishing a Morphological Database for German
%A Steiner, Petra
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F steiner-2016-refurbishing
%X The CELEX database is one of the standard lexical resources for German. It yields a wealth of data especially for phonological and morphological applications. The morphological part comprises deep-structure morphological analyses of German. However, as it was developed in the Nineties, both encoding and spelling are outdated. About one fifth of over 50,000 datasets contain umlauts and signs such as ß. Changes to a modern version cannot be obtained by simple substitution. In this paper, we shortly describe the original content and form of the orthographic and morphological database for German in CELEX. Then we present our work on modernizing the linguistic data. Lemmas and morphological analyses are transferred to a modern standard of encoding by first merging orthographic and morphological information of the lemmas and their entries and then performing a second substitution for the morphs within their morphological analyses. Changes to modern German spelling are performed by substitution rules according to orthographical standards. We show an example of the use of the data for the disambiguation of morphological structures. The discussion describes prospects of future work on this or similar lexicons. The Perl script is publicly available on our website.
%U https://aclanthology.org/L16-1176
%P 1103-1108
Markdown (Informal)
[Refurbishing a Morphological Database for German](https://aclanthology.org/L16-1176) (Steiner, LREC 2016)
ACL
- Petra Steiner. 2016. Refurbishing a Morphological Database for German. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1103–1108, Portorož, Slovenia. European Language Resources Association (ELRA).