@inproceedings{bleicken-etal-2016-using,
title = "Using a Language Technology Infrastructure for {G}erman in order to Anonymize {G}erman {S}ign {L}anguage Corpus Data",
author = "Bleicken, Julian and
Hanke, Thomas and
Salden, Uta and
Wagner, Sven",
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/L16-1526/",
pages = "3303--3306",
abstract = "For publishing sign language corpus data on the web, anonymization is crucial even if it is impossible to hide the visual appearance of the signers: In a small community, even vague references to third persons may be enough to identify those persons. In the case of the DGS Korpus (German Sign Language corpus) project, we want to publish data as a contribution to the cultural heritage of the sign language community while annotation of the data is still ongoing. This poses the question how well anonymization can be achieved given that no full linguistic analysis of the data is available. Basically, we combine analysis of all data that we have, including named entity recognition on translations into German. For this, we use the WebLicht language technology infrastructure. We report on the reliability of these methods in this special context and also illustrate how the anonymization of the video data is technically achieved in order to minimally disturb the viewer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bleicken-etal-2016-using">
<titleInfo>
<title>Using a Language Technology Infrastructure for German in order to Anonymize German Sign Language Corpus Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Bleicken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Hanke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uta</namePart>
<namePart type="family">Salden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sven</namePart>
<namePart type="family">Wagner</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>For publishing sign language corpus data on the web, anonymization is crucial even if it is impossible to hide the visual appearance of the signers: In a small community, even vague references to third persons may be enough to identify those persons. In the case of the DGS Korpus (German Sign Language corpus) project, we want to publish data as a contribution to the cultural heritage of the sign language community while annotation of the data is still ongoing. This poses the question how well anonymization can be achieved given that no full linguistic analysis of the data is available. Basically, we combine analysis of all data that we have, including named entity recognition on translations into German. For this, we use the WebLicht language technology infrastructure. We report on the reliability of these methods in this special context and also illustrate how the anonymization of the video data is technically achieved in order to minimally disturb the viewer.</abstract>
<identifier type="citekey">bleicken-etal-2016-using</identifier>
<location>
<url>https://aclanthology.org/L16-1526/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3303</start>
<end>3306</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using a Language Technology Infrastructure for German in order to Anonymize German Sign Language Corpus Data
%A Bleicken, Julian
%A Hanke, Thomas
%A Salden, Uta
%A Wagner, Sven
%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 bleicken-etal-2016-using
%X For publishing sign language corpus data on the web, anonymization is crucial even if it is impossible to hide the visual appearance of the signers: In a small community, even vague references to third persons may be enough to identify those persons. In the case of the DGS Korpus (German Sign Language corpus) project, we want to publish data as a contribution to the cultural heritage of the sign language community while annotation of the data is still ongoing. This poses the question how well anonymization can be achieved given that no full linguistic analysis of the data is available. Basically, we combine analysis of all data that we have, including named entity recognition on translations into German. For this, we use the WebLicht language technology infrastructure. We report on the reliability of these methods in this special context and also illustrate how the anonymization of the video data is technically achieved in order to minimally disturb the viewer.
%U https://aclanthology.org/L16-1526/
%P 3303-3306
Markdown (Informal)
[Using a Language Technology Infrastructure for German in order to Anonymize German Sign Language Corpus Data](https://aclanthology.org/L16-1526/) (Bleicken et al., LREC 2016)
ACL