@inproceedings{sandrelli-bendazzoli-2006-tagging,
title = "Tagging a Corpus of Interpreted Speeches: the {E}uropean Parliament Interpreting Corpus ({EPIC})",
author = "Sandrelli, Annalisa and
Bendazzoli, Claudio",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/174_pdf.pdf",
abstract = "The performance of three different taggers (Treetagger, Freeling and GRAMPAL) is evaluated on three different languages, i.e. English, Italian and Spanish. The materials are transcripts from the European Parliament Interpreting Corpus (EPIC), a corpus of original (source) and simultaneously interpreted (target) speeches. Owing to the oral nature of our materials and to the specific characteristics of spoken language produced in simultaneous interpreting, the chosen taggers have to deal with non-standard word order, disfluencies and other features not to be found in written language. Parts of the tagged sub-corpora were automatically extracted in order to assess the success rate achieved in tagging and lemmatisation. Errors and problems are discussed for each tagger, and conclusions are drawn regarding future developments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sandrelli-bendazzoli-2006-tagging">
<titleInfo>
<title>Tagging a Corpus of Interpreted Speeches: the European Parliament Interpreting Corpus (EPIC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annalisa</namePart>
<namePart type="family">Sandrelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="family">Bendazzoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The performance of three different taggers (Treetagger, Freeling and GRAMPAL) is evaluated on three different languages, i.e. English, Italian and Spanish. The materials are transcripts from the European Parliament Interpreting Corpus (EPIC), a corpus of original (source) and simultaneously interpreted (target) speeches. Owing to the oral nature of our materials and to the specific characteristics of spoken language produced in simultaneous interpreting, the chosen taggers have to deal with non-standard word order, disfluencies and other features not to be found in written language. Parts of the tagged sub-corpora were automatically extracted in order to assess the success rate achieved in tagging and lemmatisation. Errors and problems are discussed for each tagger, and conclusions are drawn regarding future developments.</abstract>
<identifier type="citekey">sandrelli-bendazzoli-2006-tagging</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/174_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tagging a Corpus of Interpreted Speeches: the European Parliament Interpreting Corpus (EPIC)
%A Sandrelli, Annalisa
%A Bendazzoli, Claudio
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F sandrelli-bendazzoli-2006-tagging
%X The performance of three different taggers (Treetagger, Freeling and GRAMPAL) is evaluated on three different languages, i.e. English, Italian and Spanish. The materials are transcripts from the European Parliament Interpreting Corpus (EPIC), a corpus of original (source) and simultaneously interpreted (target) speeches. Owing to the oral nature of our materials and to the specific characteristics of spoken language produced in simultaneous interpreting, the chosen taggers have to deal with non-standard word order, disfluencies and other features not to be found in written language. Parts of the tagged sub-corpora were automatically extracted in order to assess the success rate achieved in tagging and lemmatisation. Errors and problems are discussed for each tagger, and conclusions are drawn regarding future developments.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/174_pdf.pdf
Markdown (Informal)
[Tagging a Corpus of Interpreted Speeches: the European Parliament Interpreting Corpus (EPIC)](http://www.lrec-conf.org/proceedings/lrec2006/pdf/174_pdf.pdf) (Sandrelli & Bendazzoli, LREC 2006)
ACL