@inproceedings{goldsack-etal-2022-making,
title = "Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature",
author = "Goldsack, Tomas and
Zhang, Zhihao and
Lin, Chenghua and
Scarton, Carolina",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.724",
doi = "10.18653/v1/2022.emnlp-main.724",
pages = "10589--10604",
abstract = "Lay summarisation aims to jointly summarise and simplify a given text, thus making its content more comprehensible to non-experts.Automatic approaches for lay summarisation can provide significant value in broadening access to scientific literature, enabling a greater degree of both interdisciplinary knowledge sharing and public understanding when it comes to research findings. However, current corpora for this task are limited in their size and scope, hindering the development of broadly applicable data-driven approaches. Aiming to rectify these issues, we present two novel lay summarisation datasets, PLOS (large-scale) and eLife (medium-scale), each of which contains biomedical journal articles alongside expert-written lay summaries.We provide a thorough characterisation of our lay summaries, highlighting differing levels of readability and abstractivenessbetween datasets that can be leveraged to support the needs of different applications.Finally, we benchmark our datasets using mainstream summarisation approaches and perform a manual evaluation with domain experts, demonstrating their utility and casting light on the key challenges of this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goldsack-etal-2022-making">
<titleInfo>
<title>Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomas</namePart>
<namePart type="family">Goldsack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lay summarisation aims to jointly summarise and simplify a given text, thus making its content more comprehensible to non-experts.Automatic approaches for lay summarisation can provide significant value in broadening access to scientific literature, enabling a greater degree of both interdisciplinary knowledge sharing and public understanding when it comes to research findings. However, current corpora for this task are limited in their size and scope, hindering the development of broadly applicable data-driven approaches. Aiming to rectify these issues, we present two novel lay summarisation datasets, PLOS (large-scale) and eLife (medium-scale), each of which contains biomedical journal articles alongside expert-written lay summaries.We provide a thorough characterisation of our lay summaries, highlighting differing levels of readability and abstractivenessbetween datasets that can be leveraged to support the needs of different applications.Finally, we benchmark our datasets using mainstream summarisation approaches and perform a manual evaluation with domain experts, demonstrating their utility and casting light on the key challenges of this task.</abstract>
<identifier type="citekey">goldsack-etal-2022-making</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.724</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.724</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>10589</start>
<end>10604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature
%A Goldsack, Tomas
%A Zhang, Zhihao
%A Lin, Chenghua
%A Scarton, Carolina
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F goldsack-etal-2022-making
%X Lay summarisation aims to jointly summarise and simplify a given text, thus making its content more comprehensible to non-experts.Automatic approaches for lay summarisation can provide significant value in broadening access to scientific literature, enabling a greater degree of both interdisciplinary knowledge sharing and public understanding when it comes to research findings. However, current corpora for this task are limited in their size and scope, hindering the development of broadly applicable data-driven approaches. Aiming to rectify these issues, we present two novel lay summarisation datasets, PLOS (large-scale) and eLife (medium-scale), each of which contains biomedical journal articles alongside expert-written lay summaries.We provide a thorough characterisation of our lay summaries, highlighting differing levels of readability and abstractivenessbetween datasets that can be leveraged to support the needs of different applications.Finally, we benchmark our datasets using mainstream summarisation approaches and perform a manual evaluation with domain experts, demonstrating their utility and casting light on the key challenges of this task.
%R 10.18653/v1/2022.emnlp-main.724
%U https://aclanthology.org/2022.emnlp-main.724
%U https://doi.org/10.18653/v1/2022.emnlp-main.724
%P 10589-10604
Markdown (Informal)
[Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature](https://aclanthology.org/2022.emnlp-main.724) (Goldsack et al., EMNLP 2022)
ACL