@inproceedings{mieskes-strube-2006-part,
title = "Part-of-Speech Tagging of Transcribed Speech",
author = "Mieskes, Margot and
Strube, Michael",
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/345_pdf.pdf",
abstract = "We used four Part-of-Speech taggers, which are available for research purposes and were originally trained on text to tag a corpus of transcribed multiparty spoken dialogues. The assigned tags were then manually corrected. The correction was first used to evaluate the four taggers, then to retrain them. Despite limited resources in time, money and annotators we reached results comparable to those reported for the taggers on text. Based on our experience we present guidelines to produce reliably POS tagged corpora of new domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mieskes-strube-2006-part">
<titleInfo>
<title>Part-of-Speech Tagging of Transcribed Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Mieskes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</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>We used four Part-of-Speech taggers, which are available for research purposes and were originally trained on text to tag a corpus of transcribed multiparty spoken dialogues. The assigned tags were then manually corrected. The correction was first used to evaluate the four taggers, then to retrain them. Despite limited resources in time, money and annotators we reached results comparable to those reported for the taggers on text. Based on our experience we present guidelines to produce reliably POS tagged corpora of new domains.</abstract>
<identifier type="citekey">mieskes-strube-2006-part</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/345_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Part-of-Speech Tagging of Transcribed Speech
%A Mieskes, Margot
%A Strube, Michael
%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 mieskes-strube-2006-part
%X We used four Part-of-Speech taggers, which are available for research purposes and were originally trained on text to tag a corpus of transcribed multiparty spoken dialogues. The assigned tags were then manually corrected. The correction was first used to evaluate the four taggers, then to retrain them. Despite limited resources in time, money and annotators we reached results comparable to those reported for the taggers on text. Based on our experience we present guidelines to produce reliably POS tagged corpora of new domains.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/345_pdf.pdf
Markdown (Informal)
[Part-of-Speech Tagging of Transcribed Speech](http://www.lrec-conf.org/proceedings/lrec2006/pdf/345_pdf.pdf) (Mieskes & Strube, LREC 2006)
ACL
- Margot Mieskes and Michael Strube. 2006. Part-of-Speech Tagging of Transcribed Speech. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).