@inproceedings{luo-etal-2022-readability,
title = "Readability Controllable Biomedical Document Summarization",
author = "Luo, Zheheng and
Xie, Qianqian and
Ananiadou, Sophia",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.343",
doi = "10.18653/v1/2022.findings-emnlp.343",
pages = "4667--4680",
abstract = "Different from general documents, it is recognised that the ease with which people can understand a biomedical text is eminently varied, owing to the highly technical nature of biomedical documents and the variance of readers{'} domain knowledge. However, existing biomedical document summarization systems have paid little attention to readability control, leaving users with summaries that are incompatible with their levels of expertise.In recognition of this urgent demand, we introduce a new task of readability controllable summarization for biomedical documents, which aims to recognise users{'} readability demands and generate summaries that better suit their needs: technical summaries for experts and plain language summaries (PLS) for laymen.To establish this task, we construct a corpus consisting of biomedical papers with technical summaries and PLSs written by the authors, and benchmark multiple advanced controllable abstractive and extractive summarization models based on pre-trained language models (PLMs) with prevalent controlling and generation techniques.Moreover, we propose a novel masked language model (MLM) based metric and its variant to effectively evaluate the readability discrepancy between lay and technical summaries.Experimental results from automated and human evaluations show that though current control techniques allow for a certain degree of readability adjustment during generation, the performance of existing controllable summarization methods is far from desirable in this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2022-readability">
<titleInfo>
<title>Readability Controllable Biomedical Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheheng</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</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>Findings of the Association for Computational Linguistics: EMNLP 2022</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>Different from general documents, it is recognised that the ease with which people can understand a biomedical text is eminently varied, owing to the highly technical nature of biomedical documents and the variance of readers’ domain knowledge. However, existing biomedical document summarization systems have paid little attention to readability control, leaving users with summaries that are incompatible with their levels of expertise.In recognition of this urgent demand, we introduce a new task of readability controllable summarization for biomedical documents, which aims to recognise users’ readability demands and generate summaries that better suit their needs: technical summaries for experts and plain language summaries (PLS) for laymen.To establish this task, we construct a corpus consisting of biomedical papers with technical summaries and PLSs written by the authors, and benchmark multiple advanced controllable abstractive and extractive summarization models based on pre-trained language models (PLMs) with prevalent controlling and generation techniques.Moreover, we propose a novel masked language model (MLM) based metric and its variant to effectively evaluate the readability discrepancy between lay and technical summaries.Experimental results from automated and human evaluations show that though current control techniques allow for a certain degree of readability adjustment during generation, the performance of existing controllable summarization methods is far from desirable in this task.</abstract>
<identifier type="citekey">luo-etal-2022-readability</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.343</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.343</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4667</start>
<end>4680</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Readability Controllable Biomedical Document Summarization
%A Luo, Zheheng
%A Xie, Qianqian
%A Ananiadou, Sophia
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F luo-etal-2022-readability
%X Different from general documents, it is recognised that the ease with which people can understand a biomedical text is eminently varied, owing to the highly technical nature of biomedical documents and the variance of readers’ domain knowledge. However, existing biomedical document summarization systems have paid little attention to readability control, leaving users with summaries that are incompatible with their levels of expertise.In recognition of this urgent demand, we introduce a new task of readability controllable summarization for biomedical documents, which aims to recognise users’ readability demands and generate summaries that better suit their needs: technical summaries for experts and plain language summaries (PLS) for laymen.To establish this task, we construct a corpus consisting of biomedical papers with technical summaries and PLSs written by the authors, and benchmark multiple advanced controllable abstractive and extractive summarization models based on pre-trained language models (PLMs) with prevalent controlling and generation techniques.Moreover, we propose a novel masked language model (MLM) based metric and its variant to effectively evaluate the readability discrepancy between lay and technical summaries.Experimental results from automated and human evaluations show that though current control techniques allow for a certain degree of readability adjustment during generation, the performance of existing controllable summarization methods is far from desirable in this task.
%R 10.18653/v1/2022.findings-emnlp.343
%U https://aclanthology.org/2022.findings-emnlp.343
%U https://doi.org/10.18653/v1/2022.findings-emnlp.343
%P 4667-4680
Markdown (Informal)
[Readability Controllable Biomedical Document Summarization](https://aclanthology.org/2022.findings-emnlp.343) (Luo et al., Findings 2022)
ACL