@inproceedings{stuhrenberg-2014-extending,
title = "Extending standoff annotation",
author = {St{\"u}hrenberg, Maik},
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/308_Paper.pdf",
pages = "169--174",
abstract = "Textual information is sometimes accompanied by additional encodings (such as visuals). These multimodal documents may be interesting objects of investigation for linguistics. Another class of complex documents are pre-annotated documents. Classic XML inline annotation often fails for both document classes because of overlapping markup. However, standoff annotation, that is the separation of primary data and markup, is a valuable and common mechanism to annotate multiple hierarchies and/or read-only primary data. We demonstrate an extended version of the XStandoff meta markup language, that allows the definition of segments in spatial and pre-annotated primary data. Together with the ability to import already established (linguistic) serialization formats as annotation levels and layers in an XStandoff instance, we are able to annotate a variety of primary data files, including text, audio, still and moving images. Application scenarios that may benefit from using XStandoff are the analyzation of multimodal documents such as instruction manuals, or sports match analysis, or the less destructive cleaning of web pages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stuhrenberg-2014-extending">
<titleInfo>
<title>Extending standoff annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maik</namePart>
<namePart type="family">Stührenberg</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>Textual information is sometimes accompanied by additional encodings (such as visuals). These multimodal documents may be interesting objects of investigation for linguistics. Another class of complex documents are pre-annotated documents. Classic XML inline annotation often fails for both document classes because of overlapping markup. However, standoff annotation, that is the separation of primary data and markup, is a valuable and common mechanism to annotate multiple hierarchies and/or read-only primary data. We demonstrate an extended version of the XStandoff meta markup language, that allows the definition of segments in spatial and pre-annotated primary data. Together with the ability to import already established (linguistic) serialization formats as annotation levels and layers in an XStandoff instance, we are able to annotate a variety of primary data files, including text, audio, still and moving images. Application scenarios that may benefit from using XStandoff are the analyzation of multimodal documents such as instruction manuals, or sports match analysis, or the less destructive cleaning of web pages.</abstract>
<identifier type="citekey">stuhrenberg-2014-extending</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/308_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>169</start>
<end>174</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extending standoff annotation
%A Stührenberg, Maik
%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 stuhrenberg-2014-extending
%X Textual information is sometimes accompanied by additional encodings (such as visuals). These multimodal documents may be interesting objects of investigation for linguistics. Another class of complex documents are pre-annotated documents. Classic XML inline annotation often fails for both document classes because of overlapping markup. However, standoff annotation, that is the separation of primary data and markup, is a valuable and common mechanism to annotate multiple hierarchies and/or read-only primary data. We demonstrate an extended version of the XStandoff meta markup language, that allows the definition of segments in spatial and pre-annotated primary data. Together with the ability to import already established (linguistic) serialization formats as annotation levels and layers in an XStandoff instance, we are able to annotate a variety of primary data files, including text, audio, still and moving images. Application scenarios that may benefit from using XStandoff are the analyzation of multimodal documents such as instruction manuals, or sports match analysis, or the less destructive cleaning of web pages.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/308_Paper.pdf
%P 169-174
Markdown (Informal)
[Extending standoff annotation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/308_Paper.pdf) (Stührenberg, LREC 2014)
ACL
- Maik Stührenberg. 2014. Extending standoff annotation. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 169–174, Reykjavik, Iceland. European Language Resources Association (ELRA).