@inproceedings{amidei-etal-2019-use,
title = "The use of rating and {L}ikert scales in Natural Language Generation human evaluation tasks: A review and some recommendations",
author = "Amidei, Jacopo and
Piwek, Paul and
Willis, Alistair",
editor = "van Deemter, Kees and
Lin, Chenghua and
Takamura, Hiroya",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # "{--}" # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-8648",
doi = "10.18653/v1/W19-8648",
pages = "397--402",
abstract = "Rating and Likert scales are widely used in evaluation experiments to measure the quality of Natural Language Generation (NLG) systems. We review the use of rating and Likert scales for NLG evaluation tasks published in NLG specialized conferences over the last ten years (135 papers in total). Our analysis brings to light a number of deviations from good practice in their use. We conclude with some recommendations about the use of such scales. Our aim is to encourage the appropriate use of evaluation methodologies in the NLG community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amidei-etal-2019-use">
<titleInfo>
<title>The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacopo</namePart>
<namePart type="family">Amidei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Piwek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Willis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-oct–nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kees</namePart>
<namePart type="family">van Deemter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Rating and Likert scales are widely used in evaluation experiments to measure the quality of Natural Language Generation (NLG) systems. We review the use of rating and Likert scales for NLG evaluation tasks published in NLG specialized conferences over the last ten years (135 papers in total). Our analysis brings to light a number of deviations from good practice in their use. We conclude with some recommendations about the use of such scales. Our aim is to encourage the appropriate use of evaluation methodologies in the NLG community.</abstract>
<identifier type="citekey">amidei-etal-2019-use</identifier>
<identifier type="doi">10.18653/v1/W19-8648</identifier>
<location>
<url>https://aclanthology.org/W19-8648</url>
</location>
<part>
<date>2019-oct–nov</date>
<extent unit="page">
<start>397</start>
<end>402</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations
%A Amidei, Jacopo
%A Piwek, Paul
%A Willis, Alistair
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F amidei-etal-2019-use
%X Rating and Likert scales are widely used in evaluation experiments to measure the quality of Natural Language Generation (NLG) systems. We review the use of rating and Likert scales for NLG evaluation tasks published in NLG specialized conferences over the last ten years (135 papers in total). Our analysis brings to light a number of deviations from good practice in their use. We conclude with some recommendations about the use of such scales. Our aim is to encourage the appropriate use of evaluation methodologies in the NLG community.
%R 10.18653/v1/W19-8648
%U https://aclanthology.org/W19-8648
%U https://doi.org/10.18653/v1/W19-8648
%P 397-402
Markdown (Informal)
[The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations](https://aclanthology.org/W19-8648) (Amidei et al., INLG 2019)
ACL