@inproceedings{elhady-etal-2024-improving,
title = "Improving Factuality in Clinical Abstractive Multi-Document Summarization by Guided Continued Pre-training",
author = "Elhady, Ahmed and
Elsayed, Khaled and
Agirre, Eneko and
Artetxe, Mikel",
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 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.66",
doi = "10.18653/v1/2024.naacl-short.66",
pages = "755--761",
abstract = "Factual accuracy is an important property of neural abstractive summarization models, especially in fact-critical domains such as the clinical literature. In this work, we introduce a guided continued pre-training stage for encoder-decoder models that improves their understanding of the factual attributes of documents, which is followed by supervised fine-tuning on summarization. Our approach extends the pre-training recipe of BART to incorporate 3 additional objectives based on PICO spans, which capture the population, intervention, comparison, and outcomes related to a clinical study. Experiments on multi-document summarization in the clinical domain demonstrate that our approach is competitive with prior work, improving the quality and factuality of the summaries and achieving the best-published results in factual accuracy on the MSLR task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elhady-etal-2024-improving">
<titleInfo>
<title>Improving Factuality in Clinical Abstractive Multi-Document Summarization by Guided Continued Pre-training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Elhady</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Artetxe</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 2: Short 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>Factual accuracy is an important property of neural abstractive summarization models, especially in fact-critical domains such as the clinical literature. In this work, we introduce a guided continued pre-training stage for encoder-decoder models that improves their understanding of the factual attributes of documents, which is followed by supervised fine-tuning on summarization. Our approach extends the pre-training recipe of BART to incorporate 3 additional objectives based on PICO spans, which capture the population, intervention, comparison, and outcomes related to a clinical study. Experiments on multi-document summarization in the clinical domain demonstrate that our approach is competitive with prior work, improving the quality and factuality of the summaries and achieving the best-published results in factual accuracy on the MSLR task.</abstract>
<identifier type="citekey">elhady-etal-2024-improving</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-short.66</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-short.66</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>755</start>
<end>761</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Factuality in Clinical Abstractive Multi-Document Summarization by Guided Continued Pre-training
%A Elhady, Ahmed
%A Elsayed, Khaled
%A Agirre, Eneko
%A Artetxe, Mikel
%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 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F elhady-etal-2024-improving
%X Factual accuracy is an important property of neural abstractive summarization models, especially in fact-critical domains such as the clinical literature. In this work, we introduce a guided continued pre-training stage for encoder-decoder models that improves their understanding of the factual attributes of documents, which is followed by supervised fine-tuning on summarization. Our approach extends the pre-training recipe of BART to incorporate 3 additional objectives based on PICO spans, which capture the population, intervention, comparison, and outcomes related to a clinical study. Experiments on multi-document summarization in the clinical domain demonstrate that our approach is competitive with prior work, improving the quality and factuality of the summaries and achieving the best-published results in factual accuracy on the MSLR task.
%R 10.18653/v1/2024.naacl-short.66
%U https://aclanthology.org/2024.naacl-short.66
%U https://doi.org/10.18653/v1/2024.naacl-short.66
%P 755-761
Markdown (Informal)
[Improving Factuality in Clinical Abstractive Multi-Document Summarization by Guided Continued Pre-training](https://aclanthology.org/2024.naacl-short.66) (Elhady et al., NAACL 2024)
ACL