@inproceedings{johansson-moschitti-2010-flexible,
title = "A Flexible Representation of Heterogeneous Annotation Data",
author = "Johansson, Richard and
Moschitti, Alessandro",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/80_Paper.pdf",
abstract = "This paper describes a new flexible representation for the annotation of complex structures of metadata over heterogeneous data collections containing text and other types of media such as images or audio files. We argue that existing frameworks are not suitable for this purpose, most importantly because they do not easily generalize to multi-document and multimodal corpora, and because they often require the use of particular software frameworks. In the paper, we define a data model to represent such structured data over multimodal collections. Furthermore, we define a surface realization of the data structure as a simple and readable XML format. We present two examples of annotation tasks to illustrate how the representation and format work for complex structures involving multimodal annotation and cross-document links. The representation described here has been used in a large-scale project focusing on the annotation of a wide range of information ― from low-level features to high-level semantics ― in a multimodal data collection containing both text and images.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johansson-moschitti-2010-flexible">
<titleInfo>
<title>A Flexible Representation of Heterogeneous Annotation Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a new flexible representation for the annotation of complex structures of metadata over heterogeneous data collections containing text and other types of media such as images or audio files. We argue that existing frameworks are not suitable for this purpose, most importantly because they do not easily generalize to multi-document and multimodal corpora, and because they often require the use of particular software frameworks. In the paper, we define a data model to represent such structured data over multimodal collections. Furthermore, we define a surface realization of the data structure as a simple and readable XML format. We present two examples of annotation tasks to illustrate how the representation and format work for complex structures involving multimodal annotation and cross-document links. The representation described here has been used in a large-scale project focusing on the annotation of a wide range of information ― from low-level features to high-level semantics ― in a multimodal data collection containing both text and images.</abstract>
<identifier type="citekey">johansson-moschitti-2010-flexible</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/80_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Flexible Representation of Heterogeneous Annotation Data
%A Johansson, Richard
%A Moschitti, Alessandro
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F johansson-moschitti-2010-flexible
%X This paper describes a new flexible representation for the annotation of complex structures of metadata over heterogeneous data collections containing text and other types of media such as images or audio files. We argue that existing frameworks are not suitable for this purpose, most importantly because they do not easily generalize to multi-document and multimodal corpora, and because they often require the use of particular software frameworks. In the paper, we define a data model to represent such structured data over multimodal collections. Furthermore, we define a surface realization of the data structure as a simple and readable XML format. We present two examples of annotation tasks to illustrate how the representation and format work for complex structures involving multimodal annotation and cross-document links. The representation described here has been used in a large-scale project focusing on the annotation of a wide range of information ― from low-level features to high-level semantics ― in a multimodal data collection containing both text and images.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/80_Paper.pdf
Markdown (Informal)
[A Flexible Representation of Heterogeneous Annotation Data](http://www.lrec-conf.org/proceedings/lrec2010/pdf/80_Paper.pdf) (Johansson & Moschitti, LREC 2010)
ACL