@inproceedings{mykowiecka-etal-2010-domain,
title = "Domain-related Annotation of {P}olish Spoken Dialogue Corpus {LUNA}.{PL}",
author = "Mykowiecka, Agnieszka and
G{\l}owi{\'n}ska, Katarzyna and
Rabiega-Wi{\'s}niewska, Joanna",
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/337_Paper.pdf",
abstract = "The paper presents a corpus of Polish spoken dialogues annotated on several levels, from transcription of dialogues and their morphosyntactic analysis, to semantic annotation. The LUNA.PL corpus is the first semantically annotated corpus of Polish spontaneous speech. It contains 500 dialogues recorded at the Warsaw Transport Authority call centre. For each dialogue, the corpus contains recorded audio signal, its transcription and five XML files with annotations on subsequent levels. Speech transcription was done manually. Text annotation was constructed using a combination of rule based programmes and computer-aided manual work. For morphological annotation we used the already existing analyzer and manually disambiguated the results. Morphologically annotated texts of dialogues were automatically segmented into elementary syntactic chunks. Semantic annotation was done by a set of specially designed rules and then manually corrected. The paper describes details of the domain related semantic annotation which consists of two levels - concept level at which around 200 attributes and their values are annotated, and predicate level at which 47 frame types are recognized. We describe the domain model accepted, and the statistics over the entire annotated set of dialogues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mykowiecka-etal-2010-domain">
<titleInfo>
<title>Domain-related Annotation of Polish Spoken Dialogue Corpus LUNA.PL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Mykowiecka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarzyna</namePart>
<namePart type="family">Głowińska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Rabiega-Wiśniewska</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>The paper presents a corpus of Polish spoken dialogues annotated on several levels, from transcription of dialogues and their morphosyntactic analysis, to semantic annotation. The LUNA.PL corpus is the first semantically annotated corpus of Polish spontaneous speech. It contains 500 dialogues recorded at the Warsaw Transport Authority call centre. For each dialogue, the corpus contains recorded audio signal, its transcription and five XML files with annotations on subsequent levels. Speech transcription was done manually. Text annotation was constructed using a combination of rule based programmes and computer-aided manual work. For morphological annotation we used the already existing analyzer and manually disambiguated the results. Morphologically annotated texts of dialogues were automatically segmented into elementary syntactic chunks. Semantic annotation was done by a set of specially designed rules and then manually corrected. The paper describes details of the domain related semantic annotation which consists of two levels - concept level at which around 200 attributes and their values are annotated, and predicate level at which 47 frame types are recognized. We describe the domain model accepted, and the statistics over the entire annotated set of dialogues.</abstract>
<identifier type="citekey">mykowiecka-etal-2010-domain</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/337_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain-related Annotation of Polish Spoken Dialogue Corpus LUNA.PL
%A Mykowiecka, Agnieszka
%A Głowińska, Katarzyna
%A Rabiega-Wiśniewska, Joanna
%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 mykowiecka-etal-2010-domain
%X The paper presents a corpus of Polish spoken dialogues annotated on several levels, from transcription of dialogues and their morphosyntactic analysis, to semantic annotation. The LUNA.PL corpus is the first semantically annotated corpus of Polish spontaneous speech. It contains 500 dialogues recorded at the Warsaw Transport Authority call centre. For each dialogue, the corpus contains recorded audio signal, its transcription and five XML files with annotations on subsequent levels. Speech transcription was done manually. Text annotation was constructed using a combination of rule based programmes and computer-aided manual work. For morphological annotation we used the already existing analyzer and manually disambiguated the results. Morphologically annotated texts of dialogues were automatically segmented into elementary syntactic chunks. Semantic annotation was done by a set of specially designed rules and then manually corrected. The paper describes details of the domain related semantic annotation which consists of two levels - concept level at which around 200 attributes and their values are annotated, and predicate level at which 47 frame types are recognized. We describe the domain model accepted, and the statistics over the entire annotated set of dialogues.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/337_Paper.pdf
Markdown (Informal)
[Domain-related Annotation of Polish Spoken Dialogue Corpus LUNA.PL](http://www.lrec-conf.org/proceedings/lrec2010/pdf/337_Paper.pdf) (Mykowiecka et al., LREC 2010)
ACL