@inproceedings{nedoluzhko-etal-2022-elitr,
title = "{ELITR} Minuting Corpus: A Novel Dataset for Automatic Minuting from Multi-Party Meetings in {E}nglish and {C}zech",
author = "Nedoluzhko, Anna and
Singh, Muskaan and
Hled{\'\i}kov{\'a}, Marie and
Ghosal, Tirthankar and
Bojar, Ond{\v{r}}ej",
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-1.340",
pages = "3174--3182",
abstract = "Taking minutes is an essential component of every meeting, although the goals, style, and procedure of this activity ({``}minuting{''} for short) can vary. Minuting is a rather unstructured writing activity and is affected by who is taking the minutes and for whom the intended minutes are. With the rise of online meetings, automatic minuting would be an important benefit for the meeting participants as well as for those who might have missed the meeting. However, automatically generating meeting minutes is a challenging problem due to a variety of factors including the quality of automatic speech recorders (ASRs), availability of public meeting data, subjective knowledge of the minuter, etc. In this work, we present the first of its kind dataset on \textit{Automatic Minuting}. We develop a dataset of English and Czech technical project meetings which consists of transcripts generated from ASRs, manually corrected, and minuted by several annotators. Our dataset, AutoMin, consists of 113 (English) and 53 (Czech) meetings, covering more than 160 hours of meeting content. Upon acceptance, we will publicly release (aaa.bbb.ccc) the dataset as a set of meeting transcripts and minutes, excluding the recordings for privacy reasons. A unique feature of our dataset is that most meetings are equipped with more than one minute, each created independently. Our corpus thus allows studying differences in what people find important while taking the minutes. We also provide baseline experiments for the community to explore this novel problem further. To the best of our knowledge \textbf{AutoMin} is probably the first resource on minuting in English and also in a language other than English (Czech).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nedoluzhko-etal-2022-elitr">
<titleInfo>
<title>ELITR Minuting Corpus: A Novel Dataset for Automatic Minuting from Multi-Party Meetings in English and Czech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Nedoluzhko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muskaan</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Hledíková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</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>Taking minutes is an essential component of every meeting, although the goals, style, and procedure of this activity (“minuting” for short) can vary. Minuting is a rather unstructured writing activity and is affected by who is taking the minutes and for whom the intended minutes are. With the rise of online meetings, automatic minuting would be an important benefit for the meeting participants as well as for those who might have missed the meeting. However, automatically generating meeting minutes is a challenging problem due to a variety of factors including the quality of automatic speech recorders (ASRs), availability of public meeting data, subjective knowledge of the minuter, etc. In this work, we present the first of its kind dataset on Automatic Minuting. We develop a dataset of English and Czech technical project meetings which consists of transcripts generated from ASRs, manually corrected, and minuted by several annotators. Our dataset, AutoMin, consists of 113 (English) and 53 (Czech) meetings, covering more than 160 hours of meeting content. Upon acceptance, we will publicly release (aaa.bbb.ccc) the dataset as a set of meeting transcripts and minutes, excluding the recordings for privacy reasons. A unique feature of our dataset is that most meetings are equipped with more than one minute, each created independently. Our corpus thus allows studying differences in what people find important while taking the minutes. We also provide baseline experiments for the community to explore this novel problem further. To the best of our knowledge AutoMin is probably the first resource on minuting in English and also in a language other than English (Czech).</abstract>
<identifier type="citekey">nedoluzhko-etal-2022-elitr</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.340</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3174</start>
<end>3182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ELITR Minuting Corpus: A Novel Dataset for Automatic Minuting from Multi-Party Meetings in English and Czech
%A Nedoluzhko, Anna
%A Singh, Muskaan
%A Hledíková, Marie
%A Ghosal, Tirthankar
%A Bojar, Ondřej
%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 nedoluzhko-etal-2022-elitr
%X Taking minutes is an essential component of every meeting, although the goals, style, and procedure of this activity (“minuting” for short) can vary. Minuting is a rather unstructured writing activity and is affected by who is taking the minutes and for whom the intended minutes are. With the rise of online meetings, automatic minuting would be an important benefit for the meeting participants as well as for those who might have missed the meeting. However, automatically generating meeting minutes is a challenging problem due to a variety of factors including the quality of automatic speech recorders (ASRs), availability of public meeting data, subjective knowledge of the minuter, etc. In this work, we present the first of its kind dataset on Automatic Minuting. We develop a dataset of English and Czech technical project meetings which consists of transcripts generated from ASRs, manually corrected, and minuted by several annotators. Our dataset, AutoMin, consists of 113 (English) and 53 (Czech) meetings, covering more than 160 hours of meeting content. Upon acceptance, we will publicly release (aaa.bbb.ccc) the dataset as a set of meeting transcripts and minutes, excluding the recordings for privacy reasons. A unique feature of our dataset is that most meetings are equipped with more than one minute, each created independently. Our corpus thus allows studying differences in what people find important while taking the minutes. We also provide baseline experiments for the community to explore this novel problem further. To the best of our knowledge AutoMin is probably the first resource on minuting in English and also in a language other than English (Czech).
%U https://aclanthology.org/2022.lrec-1.340
%P 3174-3182
Markdown (Informal)
[ELITR Minuting Corpus: A Novel Dataset for Automatic Minuting from Multi-Party Meetings in English and Czech](https://aclanthology.org/2022.lrec-1.340) (Nedoluzhko et al., LREC 2022)
ACL