@inproceedings{savary-etal-2010-towards,
title = "Towards the Annotation of Named Entities in the {N}ational {C}orpus of {P}olish",
author = "Savary, Agata and
Waszczuk, Jakub and
Przepi{\'o}rkowski, Adam",
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/879_Paper.pdf",
abstract = "We present the named entity annotation task within the on-going project of the National Corpus of Polish. To the best of our knowledge, this is the first attempt at a large-scale corpus annotation of Polish named entities. We describe the scope and the TEI-inspired hierarchy of named entities admitted for this task, as well as the TEI-conformant multi-level stand-off annotation format. We also discuss some methodological strategies including the annotation of embedded, coordinated and discontinuous names. Our annotation platform consists of two main tools interconnected by converting facilities. A rule-based natural language processing platform SProUT is used for the automatic pre-annotation of named entities, due to the previously created Polish extraction grammars adapted to the annotation task. A customizable graphical tree editor TrEd, extended to our needs, provides an ergonomic environment for manual correction of annotations. Despite some difficult cases encountered in the early annotation phase, about 2,600 named entities in 1,800 corpus sentences have presently been annotated, which allowed to validate the project methodology and tools.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="savary-etal-2010-towards">
<titleInfo>
<title>Towards the Annotation of Named Entities in the National Corpus of Polish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Waszczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Przepiórkowski</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>We present the named entity annotation task within the on-going project of the National Corpus of Polish. To the best of our knowledge, this is the first attempt at a large-scale corpus annotation of Polish named entities. We describe the scope and the TEI-inspired hierarchy of named entities admitted for this task, as well as the TEI-conformant multi-level stand-off annotation format. We also discuss some methodological strategies including the annotation of embedded, coordinated and discontinuous names. Our annotation platform consists of two main tools interconnected by converting facilities. A rule-based natural language processing platform SProUT is used for the automatic pre-annotation of named entities, due to the previously created Polish extraction grammars adapted to the annotation task. A customizable graphical tree editor TrEd, extended to our needs, provides an ergonomic environment for manual correction of annotations. Despite some difficult cases encountered in the early annotation phase, about 2,600 named entities in 1,800 corpus sentences have presently been annotated, which allowed to validate the project methodology and tools.</abstract>
<identifier type="citekey">savary-etal-2010-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/879_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards the Annotation of Named Entities in the National Corpus of Polish
%A Savary, Agata
%A Waszczuk, Jakub
%A Przepiórkowski, Adam
%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 savary-etal-2010-towards
%X We present the named entity annotation task within the on-going project of the National Corpus of Polish. To the best of our knowledge, this is the first attempt at a large-scale corpus annotation of Polish named entities. We describe the scope and the TEI-inspired hierarchy of named entities admitted for this task, as well as the TEI-conformant multi-level stand-off annotation format. We also discuss some methodological strategies including the annotation of embedded, coordinated and discontinuous names. Our annotation platform consists of two main tools interconnected by converting facilities. A rule-based natural language processing platform SProUT is used for the automatic pre-annotation of named entities, due to the previously created Polish extraction grammars adapted to the annotation task. A customizable graphical tree editor TrEd, extended to our needs, provides an ergonomic environment for manual correction of annotations. Despite some difficult cases encountered in the early annotation phase, about 2,600 named entities in 1,800 corpus sentences have presently been annotated, which allowed to validate the project methodology and tools.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/879_Paper.pdf
Markdown (Informal)
[Towards the Annotation of Named Entities in the National Corpus of Polish](http://www.lrec-conf.org/proceedings/lrec2010/pdf/879_Paper.pdf) (Savary et al., LREC 2010)
ACL