@inproceedings{hu-etal-2023-meetingbank,
title = "{M}eeting{B}ank: A Benchmark Dataset for Meeting Summarization",
author = "Hu, Yebowen and
Ganter, Timothy and
Deilamsalehy, Hanieh and
Dernoncourt, Franck and
Foroosh, Hassan and
Liu, Fei",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.906",
doi = "10.18653/v1/2023.acl-long.906",
pages = "16409--16423",
abstract = "As the number of recorded meetings increases, it becomes increasingly important to utilize summarization technology to create useful summaries of these recordings. However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential. Furthermore, meeting summaries written by experienced writers are scarce, making it hard for abstractive summarizers to produce sensible output without a reliable reference. This lack of annotated corpora has hindered the development of meeting summarization technology. In this paper, we present MeetingBank, a new benchmark dataset of city council meetings over the past decade. MeetingBank is unique among other meeting corpora due to its divide-and-conquer approach, which involves dividing professionally written meeting minutes into shorter passages and aligning them with specific segments of the meeting. This breaks down the process of summarizing a lengthy meeting into smaller, more manageable tasks. The dataset provides a new testbed of various meeting summarization systems and also allows the public to gain insight into how council decisions are made. We make the collection, including meeting video links, transcripts, reference summaries, agenda, and other metadata, publicly available to facilitate the development of better meeting summarization techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2023-meetingbank">
<titleInfo>
<title>MeetingBank: A Benchmark Dataset for Meeting Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yebowen</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Ganter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanieh</namePart>
<namePart type="family">Deilamsalehy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Foroosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As the number of recorded meetings increases, it becomes increasingly important to utilize summarization technology to create useful summaries of these recordings. However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential. Furthermore, meeting summaries written by experienced writers are scarce, making it hard for abstractive summarizers to produce sensible output without a reliable reference. This lack of annotated corpora has hindered the development of meeting summarization technology. In this paper, we present MeetingBank, a new benchmark dataset of city council meetings over the past decade. MeetingBank is unique among other meeting corpora due to its divide-and-conquer approach, which involves dividing professionally written meeting minutes into shorter passages and aligning them with specific segments of the meeting. This breaks down the process of summarizing a lengthy meeting into smaller, more manageable tasks. The dataset provides a new testbed of various meeting summarization systems and also allows the public to gain insight into how council decisions are made. We make the collection, including meeting video links, transcripts, reference summaries, agenda, and other metadata, publicly available to facilitate the development of better meeting summarization techniques.</abstract>
<identifier type="citekey">hu-etal-2023-meetingbank</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.906</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.906</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>16409</start>
<end>16423</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MeetingBank: A Benchmark Dataset for Meeting Summarization
%A Hu, Yebowen
%A Ganter, Timothy
%A Deilamsalehy, Hanieh
%A Dernoncourt, Franck
%A Foroosh, Hassan
%A Liu, Fei
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F hu-etal-2023-meetingbank
%X As the number of recorded meetings increases, it becomes increasingly important to utilize summarization technology to create useful summaries of these recordings. However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential. Furthermore, meeting summaries written by experienced writers are scarce, making it hard for abstractive summarizers to produce sensible output without a reliable reference. This lack of annotated corpora has hindered the development of meeting summarization technology. In this paper, we present MeetingBank, a new benchmark dataset of city council meetings over the past decade. MeetingBank is unique among other meeting corpora due to its divide-and-conquer approach, which involves dividing professionally written meeting minutes into shorter passages and aligning them with specific segments of the meeting. This breaks down the process of summarizing a lengthy meeting into smaller, more manageable tasks. The dataset provides a new testbed of various meeting summarization systems and also allows the public to gain insight into how council decisions are made. We make the collection, including meeting video links, transcripts, reference summaries, agenda, and other metadata, publicly available to facilitate the development of better meeting summarization techniques.
%R 10.18653/v1/2023.acl-long.906
%U https://aclanthology.org/2023.acl-long.906
%U https://doi.org/10.18653/v1/2023.acl-long.906
%P 16409-16423
Markdown (Informal)
[MeetingBank: A Benchmark Dataset for Meeting Summarization](https://aclanthology.org/2023.acl-long.906) (Hu et al., ACL 2023)
ACL
- Yebowen Hu, Timothy Ganter, Hanieh Deilamsalehy, Franck Dernoncourt, Hassan Foroosh, and Fei Liu. 2023. MeetingBank: A Benchmark Dataset for Meeting Summarization. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16409–16423, Toronto, Canada. Association for Computational Linguistics.