@inproceedings{pezik-etal-2022-diabiz,
title = "{D}ia{B}iz {--} an Annotated Corpus of {P}olish Call Center Dialogs",
author = "P{\k{e}}zik, Piotr and
Krawentek, Gosia and
Karasi{\'n}ska, Sylwia and
Wilk, Pawe{\l} and
Rybi{\'n}ska, Paulina and
Cichosz, Anna and
Peljak-{\L}api{\'n}ska, Angelika and
Deckert, Miko{\l}aj and
Adamczyk, Micha{\l}",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.76",
pages = "723--726",
abstract = "This paper introduces DiaBiz, a large, annotated, multimodal corpus of Polish telephone conversations conducted in varied business settings, comprising 4036 call centre interactions from nine different domains, i.e. banking, energy services, telecommunications, insurance, medical care, debt collection, tourism, retail and car rental. The corpus was developed to boost the development of third-party speech recognition engines, dialog systems and conversational intelligence tools for Polish. Its current size amounts to nearly 410 hours of recordings and over 3 million words of transcribed speech. We present the structure of the corpus, data collection and transcription procedures, challenges of punctuating and truecasing speech transcripts, dialog structure annotation and discuss some of the ecological validity considerations involved in the development of such resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pezik-etal-2022-diabiz">
<titleInfo>
<title>DiaBiz – an Annotated Corpus of Polish Call Center Dialogs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Pęzik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gosia</namePart>
<namePart type="family">Krawentek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylwia</namePart>
<namePart type="family">Karasińska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Wilk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paulina</namePart>
<namePart type="family">Rybińska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Cichosz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelika</namePart>
<namePart type="family">Peljak-Łapińska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikołaj</namePart>
<namePart type="family">Deckert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Adamczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces DiaBiz, a large, annotated, multimodal corpus of Polish telephone conversations conducted in varied business settings, comprising 4036 call centre interactions from nine different domains, i.e. banking, energy services, telecommunications, insurance, medical care, debt collection, tourism, retail and car rental. The corpus was developed to boost the development of third-party speech recognition engines, dialog systems and conversational intelligence tools for Polish. Its current size amounts to nearly 410 hours of recordings and over 3 million words of transcribed speech. We present the structure of the corpus, data collection and transcription procedures, challenges of punctuating and truecasing speech transcripts, dialog structure annotation and discuss some of the ecological validity considerations involved in the development of such resources.</abstract>
<identifier type="citekey">pezik-etal-2022-diabiz</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.76</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>723</start>
<end>726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiaBiz – an Annotated Corpus of Polish Call Center Dialogs
%A Pęzik, Piotr
%A Krawentek, Gosia
%A Karasińska, Sylwia
%A Wilk, Paweł
%A Rybińska, Paulina
%A Cichosz, Anna
%A Peljak-Łapińska, Angelika
%A Deckert, Mikołaj
%A Adamczyk, Michał
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F pezik-etal-2022-diabiz
%X This paper introduces DiaBiz, a large, annotated, multimodal corpus of Polish telephone conversations conducted in varied business settings, comprising 4036 call centre interactions from nine different domains, i.e. banking, energy services, telecommunications, insurance, medical care, debt collection, tourism, retail and car rental. The corpus was developed to boost the development of third-party speech recognition engines, dialog systems and conversational intelligence tools for Polish. Its current size amounts to nearly 410 hours of recordings and over 3 million words of transcribed speech. We present the structure of the corpus, data collection and transcription procedures, challenges of punctuating and truecasing speech transcripts, dialog structure annotation and discuss some of the ecological validity considerations involved in the development of such resources.
%U https://aclanthology.org/2022.lrec-1.76
%P 723-726
Markdown (Informal)
[DiaBiz – an Annotated Corpus of Polish Call Center Dialogs](https://aclanthology.org/2022.lrec-1.76) (Pęzik et al., LREC 2022)
ACL
- Piotr Pęzik, Gosia Krawentek, Sylwia Karasińska, Paweł Wilk, Paulina Rybińska, Anna Cichosz, Angelika Peljak-Łapińska, Mikołaj Deckert, and Michał Adamczyk. 2022. DiaBiz – an Annotated Corpus of Polish Call Center Dialogs. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 723–726, Marseille, France. European Language Resources Association.