@inproceedings{scheible-etal-2012-gatetogermanc,
title = "{GATE}to{G}er{M}an{C}: A {GATE}-based Annotation Pipeline for Historical {G}erman",
author = "Scheible, Silke and
Whitt, Richard J. and
Durrell, Martin and
Bennett, Paul",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/978_Paper.pdf",
pages = "3611--3617",
abstract = "We describe a new GATE-based linguistic annotation pipeline for Early Modern German, which can be used to annotate historical texts with word tokens, sentence boundaries, lemmas, and POS tags. The pipeline is based on a customisation of the freely available ANNIE system for English (Cunningham et al., 2002), in combination with a version of the TreeTagger (Schmid, 1994) trained on gold standard Early Modern German data. The POS-tagging and lemmatisation components of the pipeline achieve an average accuracy of 89.44{\%} and 83.16{\%}, respectively, on unseen historical data from various genres and publication dates within the Early Modern period. We show that normalisation of spelling variation can further improve these results. With no specialised tools available for processing this particular stage of the language, this pipeline will be of particular interest to smaller, humanities-based projects wishing to add linguistic annotations to their historical data but which lack the means or resources to develop such tools themselves.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scheible-etal-2012-gatetogermanc">
<titleInfo>
<title>GATEtoGerManC: A GATE-based Annotation Pipeline for Historical German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silke</namePart>
<namePart type="family">Scheible</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Whitt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Durrell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Bennett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe a new GATE-based linguistic annotation pipeline for Early Modern German, which can be used to annotate historical texts with word tokens, sentence boundaries, lemmas, and POS tags. The pipeline is based on a customisation of the freely available ANNIE system for English (Cunningham et al., 2002), in combination with a version of the TreeTagger (Schmid, 1994) trained on gold standard Early Modern German data. The POS-tagging and lemmatisation components of the pipeline achieve an average accuracy of 89.44% and 83.16%, respectively, on unseen historical data from various genres and publication dates within the Early Modern period. We show that normalisation of spelling variation can further improve these results. With no specialised tools available for processing this particular stage of the language, this pipeline will be of particular interest to smaller, humanities-based projects wishing to add linguistic annotations to their historical data but which lack the means or resources to develop such tools themselves.</abstract>
<identifier type="citekey">scheible-etal-2012-gatetogermanc</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/978_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3611</start>
<end>3617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GATEtoGerManC: A GATE-based Annotation Pipeline for Historical German
%A Scheible, Silke
%A Whitt, Richard J.
%A Durrell, Martin
%A Bennett, Paul
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F scheible-etal-2012-gatetogermanc
%X We describe a new GATE-based linguistic annotation pipeline for Early Modern German, which can be used to annotate historical texts with word tokens, sentence boundaries, lemmas, and POS tags. The pipeline is based on a customisation of the freely available ANNIE system for English (Cunningham et al., 2002), in combination with a version of the TreeTagger (Schmid, 1994) trained on gold standard Early Modern German data. The POS-tagging and lemmatisation components of the pipeline achieve an average accuracy of 89.44% and 83.16%, respectively, on unseen historical data from various genres and publication dates within the Early Modern period. We show that normalisation of spelling variation can further improve these results. With no specialised tools available for processing this particular stage of the language, this pipeline will be of particular interest to smaller, humanities-based projects wishing to add linguistic annotations to their historical data but which lack the means or resources to develop such tools themselves.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/978_Paper.pdf
%P 3611-3617
Markdown (Informal)
[GATEtoGerManC: A GATE-based Annotation Pipeline for Historical German](http://www.lrec-conf.org/proceedings/lrec2012/pdf/978_Paper.pdf) (Scheible et al., LREC 2012)
ACL