@inproceedings{peper-etal-2024-pelms,
title = "{PELMS}: Pre-training for Effective Low-Shot Multi-Document Summarization",
author = "Peper, Joseph and
Qiu, Wenzhao and
Wang, Lu",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.423",
pages = "7652--7674",
abstract = "We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information salience for pre-training strategy design, they struggle to generate abstractive and reflective summaries, which are critical properties for MDS. To this end, we present **PELMS**, a pre-trained model that uses pre-training objectives based on semantic coherence heuristics and faithfulness constraints together with unlabeled multi-document inputs, to promote the generation of concise, fluent, and faithful summaries. To support the training of PELMS, we compile **MultiPT**, a multi-document pre-training corpus containing over 93 million documents to form more than 3million unlabeled topic-centric document clusters, covering diverse genres such as product reviews, news, and general knowledge. We perform extensive evaluation of PELMS in low-shot settings on a wide range of MDS datasets. Our approach consistently outperforms competitive comparisons with respect to overall informativeness, abstractiveness, coherence, and faithfulness, and with minimal fine-tuning can match performance of language models at a much larger scale (e.g., GPT-4).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peper-etal-2024-pelms">
<titleInfo>
<title>PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Peper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenzhao</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information salience for pre-training strategy design, they struggle to generate abstractive and reflective summaries, which are critical properties for MDS. To this end, we present **PELMS**, a pre-trained model that uses pre-training objectives based on semantic coherence heuristics and faithfulness constraints together with unlabeled multi-document inputs, to promote the generation of concise, fluent, and faithful summaries. To support the training of PELMS, we compile **MultiPT**, a multi-document pre-training corpus containing over 93 million documents to form more than 3million unlabeled topic-centric document clusters, covering diverse genres such as product reviews, news, and general knowledge. We perform extensive evaluation of PELMS in low-shot settings on a wide range of MDS datasets. Our approach consistently outperforms competitive comparisons with respect to overall informativeness, abstractiveness, coherence, and faithfulness, and with minimal fine-tuning can match performance of language models at a much larger scale (e.g., GPT-4).</abstract>
<identifier type="citekey">peper-etal-2024-pelms</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.423</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>7652</start>
<end>7674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization
%A Peper, Joseph
%A Qiu, Wenzhao
%A Wang, Lu
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F peper-etal-2024-pelms
%X We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information salience for pre-training strategy design, they struggle to generate abstractive and reflective summaries, which are critical properties for MDS. To this end, we present **PELMS**, a pre-trained model that uses pre-training objectives based on semantic coherence heuristics and faithfulness constraints together with unlabeled multi-document inputs, to promote the generation of concise, fluent, and faithful summaries. To support the training of PELMS, we compile **MultiPT**, a multi-document pre-training corpus containing over 93 million documents to form more than 3million unlabeled topic-centric document clusters, covering diverse genres such as product reviews, news, and general knowledge. We perform extensive evaluation of PELMS in low-shot settings on a wide range of MDS datasets. Our approach consistently outperforms competitive comparisons with respect to overall informativeness, abstractiveness, coherence, and faithfulness, and with minimal fine-tuning can match performance of language models at a much larger scale (e.g., GPT-4).
%U https://aclanthology.org/2024.naacl-long.423
%P 7652-7674
Markdown (Informal)
[PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization](https://aclanthology.org/2024.naacl-long.423) (Peper et al., NAACL 2024)
ACL
- Joseph Peper, Wenzhao Qiu, and Lu Wang. 2024. PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7652–7674, Mexico City, Mexico. Association for Computational Linguistics.