@inproceedings{kirstein-etal-2024-whats,
title = "What{'}s under the hood: Investigating Automatic Metrics on Meeting Summarization",
author = "Kirstein, Frederic and
Wahle, Jan Philip and
Ruas, Terry and
Gipp, Bela",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.393",
doi = "10.18653/v1/2024.findings-emnlp.393",
pages = "6709--6723",
abstract = "Meeting summarization has become a critical task considering the increase in online interactions. Despite new techniques being proposed regularly, the evaluation of meeting summarization techniques relies on metrics not tailored to capture meeting-specific errors, leading to ineffective assessment. This paper explores what established automatic metrics capture and the errors they mask by correlating metric scores with human evaluations across a comprehensive error taxonomy. We start by reviewing the literature on English meeting summarization to identify key challenges, such as speaker dynamics and contextual turn-taking, and error types, including missing information and linguistic inaccuracy, concepts previously loosely defined in the field. We then examine the relationship between these challenges and errors using human annotated transcripts and summaries from encoder-decoder-based and autoregressive Transformer models on the QMSum dataset. Experiments reveal that different model architectures respond variably to the challenges, resulting in distinct links between challenges and errors. Current established metrics struggle to capture the observable errors, showing weak to moderate correlations, with a third of the correlations indicating error masking. Only a subset of metrics accurately reacts to specific errors, while most correlations show either unresponsiveness or failure to reflect the error{'}s impact on summary quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kirstein-etal-2024-whats">
<titleInfo>
<title>What’s under the hood: Investigating Automatic Metrics on Meeting Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Kirstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Philip</namePart>
<namePart type="family">Wahle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Ruas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bela</namePart>
<namePart type="family">Gipp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Meeting summarization has become a critical task considering the increase in online interactions. Despite new techniques being proposed regularly, the evaluation of meeting summarization techniques relies on metrics not tailored to capture meeting-specific errors, leading to ineffective assessment. This paper explores what established automatic metrics capture and the errors they mask by correlating metric scores with human evaluations across a comprehensive error taxonomy. We start by reviewing the literature on English meeting summarization to identify key challenges, such as speaker dynamics and contextual turn-taking, and error types, including missing information and linguistic inaccuracy, concepts previously loosely defined in the field. We then examine the relationship between these challenges and errors using human annotated transcripts and summaries from encoder-decoder-based and autoregressive Transformer models on the QMSum dataset. Experiments reveal that different model architectures respond variably to the challenges, resulting in distinct links between challenges and errors. Current established metrics struggle to capture the observable errors, showing weak to moderate correlations, with a third of the correlations indicating error masking. Only a subset of metrics accurately reacts to specific errors, while most correlations show either unresponsiveness or failure to reflect the error’s impact on summary quality.</abstract>
<identifier type="citekey">kirstein-etal-2024-whats</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.393</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.393</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>6709</start>
<end>6723</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What’s under the hood: Investigating Automatic Metrics on Meeting Summarization
%A Kirstein, Frederic
%A Wahle, Jan Philip
%A Ruas, Terry
%A Gipp, Bela
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F kirstein-etal-2024-whats
%X Meeting summarization has become a critical task considering the increase in online interactions. Despite new techniques being proposed regularly, the evaluation of meeting summarization techniques relies on metrics not tailored to capture meeting-specific errors, leading to ineffective assessment. This paper explores what established automatic metrics capture and the errors they mask by correlating metric scores with human evaluations across a comprehensive error taxonomy. We start by reviewing the literature on English meeting summarization to identify key challenges, such as speaker dynamics and contextual turn-taking, and error types, including missing information and linguistic inaccuracy, concepts previously loosely defined in the field. We then examine the relationship between these challenges and errors using human annotated transcripts and summaries from encoder-decoder-based and autoregressive Transformer models on the QMSum dataset. Experiments reveal that different model architectures respond variably to the challenges, resulting in distinct links between challenges and errors. Current established metrics struggle to capture the observable errors, showing weak to moderate correlations, with a third of the correlations indicating error masking. Only a subset of metrics accurately reacts to specific errors, while most correlations show either unresponsiveness or failure to reflect the error’s impact on summary quality.
%R 10.18653/v1/2024.findings-emnlp.393
%U https://aclanthology.org/2024.findings-emnlp.393
%U https://doi.org/10.18653/v1/2024.findings-emnlp.393
%P 6709-6723
Markdown (Informal)
[What’s under the hood: Investigating Automatic Metrics on Meeting Summarization](https://aclanthology.org/2024.findings-emnlp.393) (Kirstein et al., Findings 2024)
ACL