@inproceedings{wu-etal-2023-vcsum,
title = "{VCSUM}: A Versatile {C}hinese Meeting Summarization Dataset",
author = "Wu, Han and
Zhan, Mingjie and
Tan, Haochen and
Hou, Zhaohui and
Liang, Ding and
Song, Linqi",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.377",
doi = "10.18653/v1/2023.findings-acl.377",
pages = "6065--6079",
abstract = "Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting summarization dataset, dubbed VCSum, consisting of 239 real-life meetings, with a total duration of over 230 hours. We claim our dataset is versatile because we provide the annotations of topic segmentation, headlines, segmentation summaries, overall meeting summaries, and salient sentences for each meeting transcript. As such, the dataset can adapt to various summarization tasks or methods, including segmentation-based summarization, multi-granularity summarization and retrieval-then-generate summarization. Our analysis confirms the effectiveness and robustness of VCSum. We also provide a set of benchmark models regarding different downstream summarization tasks on VCSum to facilitate further research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-vcsum">
<titleInfo>
<title>VCSUM: A Versatile Chinese Meeting Summarization Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingjie</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haochen</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaohui</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ding</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linqi</namePart>
<namePart type="family">Song</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>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting summarization dataset, dubbed VCSum, consisting of 239 real-life meetings, with a total duration of over 230 hours. We claim our dataset is versatile because we provide the annotations of topic segmentation, headlines, segmentation summaries, overall meeting summaries, and salient sentences for each meeting transcript. As such, the dataset can adapt to various summarization tasks or methods, including segmentation-based summarization, multi-granularity summarization and retrieval-then-generate summarization. Our analysis confirms the effectiveness and robustness of VCSum. We also provide a set of benchmark models regarding different downstream summarization tasks on VCSum to facilitate further research.</abstract>
<identifier type="citekey">wu-etal-2023-vcsum</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.377</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.377</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6065</start>
<end>6079</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VCSUM: A Versatile Chinese Meeting Summarization Dataset
%A Wu, Han
%A Zhan, Mingjie
%A Tan, Haochen
%A Hou, Zhaohui
%A Liang, Ding
%A Song, Linqi
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wu-etal-2023-vcsum
%X Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting summarization dataset, dubbed VCSum, consisting of 239 real-life meetings, with a total duration of over 230 hours. We claim our dataset is versatile because we provide the annotations of topic segmentation, headlines, segmentation summaries, overall meeting summaries, and salient sentences for each meeting transcript. As such, the dataset can adapt to various summarization tasks or methods, including segmentation-based summarization, multi-granularity summarization and retrieval-then-generate summarization. Our analysis confirms the effectiveness and robustness of VCSum. We also provide a set of benchmark models regarding different downstream summarization tasks on VCSum to facilitate further research.
%R 10.18653/v1/2023.findings-acl.377
%U https://aclanthology.org/2023.findings-acl.377
%U https://doi.org/10.18653/v1/2023.findings-acl.377
%P 6065-6079
Markdown (Informal)
[VCSUM: A Versatile Chinese Meeting Summarization Dataset](https://aclanthology.org/2023.findings-acl.377) (Wu et al., Findings 2023)
ACL
- Han Wu, Mingjie Zhan, Haochen Tan, Zhaohui Hou, Ding Liang, and Linqi Song. 2023. VCSUM: A Versatile Chinese Meeting Summarization Dataset. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6065–6079, Toronto, Canada. Association for Computational Linguistics.