@inproceedings{moramarco-etal-2021-towards,
title = "Towards Objectively Evaluating the Quality of Generated Medical Summaries",
author = "Moramarco, Francesco and
Juric, Damir and
Savkov, Aleksandar and
Reiter, Ehud",
editor = "Belz, Anya and
Agarwal, Shubham and
Graham, Yvette and
Reiter, Ehud and
Shimorina, Anastasia",
booktitle = "Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.humeval-1.6",
pages = "56--61",
abstract = "We propose a method for evaluating the quality of generated text by asking evaluators to count facts, and computing precision, recall, f-score, and accuracy from the raw counts. We believe this approach leads to a more objective and easier to reproduce evaluation. We apply this to the task of medical report summarisation, where measuring objective quality and accuracy is of paramount importance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moramarco-etal-2021-towards">
<titleInfo>
<title>Towards Objectively Evaluating the Quality of Generated Medical Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Moramarco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damir</namePart>
<namePart type="family">Juric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandar</namePart>
<namePart type="family">Savkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</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">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a method for evaluating the quality of generated text by asking evaluators to count facts, and computing precision, recall, f-score, and accuracy from the raw counts. We believe this approach leads to a more objective and easier to reproduce evaluation. We apply this to the task of medical report summarisation, where measuring objective quality and accuracy is of paramount importance.</abstract>
<identifier type="citekey">moramarco-etal-2021-towards</identifier>
<location>
<url>https://aclanthology.org/2021.humeval-1.6</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>56</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Objectively Evaluating the Quality of Generated Medical Summaries
%A Moramarco, Francesco
%A Juric, Damir
%A Savkov, Aleksandar
%A Reiter, Ehud
%Y Belz, Anya
%Y Agarwal, Shubham
%Y Graham, Yvette
%Y Reiter, Ehud
%Y Shimorina, Anastasia
%S Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F moramarco-etal-2021-towards
%X We propose a method for evaluating the quality of generated text by asking evaluators to count facts, and computing precision, recall, f-score, and accuracy from the raw counts. We believe this approach leads to a more objective and easier to reproduce evaluation. We apply this to the task of medical report summarisation, where measuring objective quality and accuracy is of paramount importance.
%U https://aclanthology.org/2021.humeval-1.6
%P 56-61
Markdown (Informal)
[Towards Objectively Evaluating the Quality of Generated Medical Summaries](https://aclanthology.org/2021.humeval-1.6) (Moramarco et al., HumEval 2021)
ACL