@inproceedings{kirstein-etal-2024-tell,
title = "Tell me what {I} need to know: Exploring {LLM}-based (Personalized) Abstractive Multi-Source Meeting Summarization",
author = "Kirstein, Frederic and
Ruas, Terry and
Kratel, Robert and
Gipp, Bela",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.69",
pages = "920--939",
abstract = "Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings{'} content.Previous attempts to address these issues by considering related supplementary resources (e.g., presentation slides) alongside transcripts are hindered by models{'} limited context sizes and handling the additional complexities of the multi-source tasks, such as identifying relevant information in additional files and seamlessly aligning it with the meeting content.This work explores multi-source meeting summarization considering supplementary materials through a three-stage large language model approach: identifying transcript passages needing additional context, inferring relevant details from supplementary materials and inserting them into the transcript, and generating a summary from this enriched transcript.Our multi-source approach enhances model understanding, increasing summary relevance by {\textasciitilde}9{\%} and producing more content-rich outputs.We introduce a personalization protocol that extracts participant characteristics and tailors summaries accordingly, improving informativeness by {\textasciitilde}10{\%}.This work further provides insights on performance-cost trade-offs across four leading model families, including edge-device capable options.Our approach can be extended to similar complex generative tasks benefitting from additional resources and personalization, such as dialogue systems and action planning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kirstein-etal-2024-tell">
<titleInfo>
<title>Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source 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">Terry</namePart>
<namePart type="family">Ruas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Kratel</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoţiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings’ content.Previous attempts to address these issues by considering related supplementary resources (e.g., presentation slides) alongside transcripts are hindered by models’ limited context sizes and handling the additional complexities of the multi-source tasks, such as identifying relevant information in additional files and seamlessly aligning it with the meeting content.This work explores multi-source meeting summarization considering supplementary materials through a three-stage large language model approach: identifying transcript passages needing additional context, inferring relevant details from supplementary materials and inserting them into the transcript, and generating a summary from this enriched transcript.Our multi-source approach enhances model understanding, increasing summary relevance by ~9% and producing more content-rich outputs.We introduce a personalization protocol that extracts participant characteristics and tailors summaries accordingly, improving informativeness by ~10%.This work further provides insights on performance-cost trade-offs across four leading model families, including edge-device capable options.Our approach can be extended to similar complex generative tasks benefitting from additional resources and personalization, such as dialogue systems and action planning.</abstract>
<identifier type="citekey">kirstein-etal-2024-tell</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-industry.69</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>920</start>
<end>939</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization
%A Kirstein, Frederic
%A Ruas, Terry
%A Kratel, Robert
%A Gipp, Bela
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F kirstein-etal-2024-tell
%X Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings’ content.Previous attempts to address these issues by considering related supplementary resources (e.g., presentation slides) alongside transcripts are hindered by models’ limited context sizes and handling the additional complexities of the multi-source tasks, such as identifying relevant information in additional files and seamlessly aligning it with the meeting content.This work explores multi-source meeting summarization considering supplementary materials through a three-stage large language model approach: identifying transcript passages needing additional context, inferring relevant details from supplementary materials and inserting them into the transcript, and generating a summary from this enriched transcript.Our multi-source approach enhances model understanding, increasing summary relevance by ~9% and producing more content-rich outputs.We introduce a personalization protocol that extracts participant characteristics and tailors summaries accordingly, improving informativeness by ~10%.This work further provides insights on performance-cost trade-offs across four leading model families, including edge-device capable options.Our approach can be extended to similar complex generative tasks benefitting from additional resources and personalization, such as dialogue systems and action planning.
%U https://aclanthology.org/2024.emnlp-industry.69
%P 920-939
Markdown (Informal)
[Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization](https://aclanthology.org/2024.emnlp-industry.69) (Kirstein et al., EMNLP 2024)
ACL