@inproceedings{viszlay-etal-2016-extension,
title = "An Extension of the {S}lovak Broadcast News Corpus based on Semi-Automatic Annotation",
author = "Viszlay, Peter and
Sta{\v{s}}, J{\'a}n and
Koct{\'u}r, Tom{\'a}{\v{s}} and
Lojka, Martin and
Juh{\'a}r, Jozef",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1743",
pages = "4684--4687",
abstract = "In this paper, we introduce an extension of our previously released TUKE-BNews-SK corpus based on a semi-automatic annotation scheme. It firstly relies on the automatic transcription of the BN data performed by our Slovak large vocabulary continuous speech recognition system. The generated hypotheses are then manually corrected and completed by trained human annotators. The corpus is composed of 25 hours of fully-annotated spontaneous and prepared speech. In addition, we have acquired 900 hours of another BN data, part of which we plan to annotate semi-automatically. We present a preliminary corpus evaluation that gives very promising results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="viszlay-etal-2016-extension">
<titleInfo>
<title>An Extension of the Slovak Broadcast News Corpus based on Semi-Automatic Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Viszlay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ján</namePart>
<namePart type="family">Staš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Koctúr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Lojka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jozef</namePart>
<namePart type="family">Juhár</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce an extension of our previously released TUKE-BNews-SK corpus based on a semi-automatic annotation scheme. It firstly relies on the automatic transcription of the BN data performed by our Slovak large vocabulary continuous speech recognition system. The generated hypotheses are then manually corrected and completed by trained human annotators. The corpus is composed of 25 hours of fully-annotated spontaneous and prepared speech. In addition, we have acquired 900 hours of another BN data, part of which we plan to annotate semi-automatically. We present a preliminary corpus evaluation that gives very promising results.</abstract>
<identifier type="citekey">viszlay-etal-2016-extension</identifier>
<location>
<url>https://aclanthology.org/L16-1743</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4684</start>
<end>4687</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Extension of the Slovak Broadcast News Corpus based on Semi-Automatic Annotation
%A Viszlay, Peter
%A Staš, Ján
%A Koctúr, Tomáš
%A Lojka, Martin
%A Juhár, Jozef
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F viszlay-etal-2016-extension
%X In this paper, we introduce an extension of our previously released TUKE-BNews-SK corpus based on a semi-automatic annotation scheme. It firstly relies on the automatic transcription of the BN data performed by our Slovak large vocabulary continuous speech recognition system. The generated hypotheses are then manually corrected and completed by trained human annotators. The corpus is composed of 25 hours of fully-annotated spontaneous and prepared speech. In addition, we have acquired 900 hours of another BN data, part of which we plan to annotate semi-automatically. We present a preliminary corpus evaluation that gives very promising results.
%U https://aclanthology.org/L16-1743
%P 4684-4687
Markdown (Informal)
[An Extension of the Slovak Broadcast News Corpus based on Semi-Automatic Annotation](https://aclanthology.org/L16-1743) (Viszlay et al., LREC 2016)
ACL