@inproceedings{lai-etal-2022-human,
title = "Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer",
author = "Lai, Huiyuan and
Mao, Jiali and
Toral, Antonio and
Nissim, Malvina",
editor = "Belz, Anya and
Popovi{\'c}, Maja and
Reiter, Ehud and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.humeval-1.9",
doi = "10.18653/v1/2022.humeval-1.9",
pages = "102--115",
abstract = "Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human judgement. We focus on the task of formality transfer, and on the three aspects that are usually evaluated: style strength, content preservation, and fluency. To cast light on how such aspects are assessed by common and new metrics, we run a human-based evaluation and perform a rich correlation analysis. We are then able to offer some recommendations on the use of such metrics in formality transfer, also with an eye to their generalisability (or not) to related tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lai-etal-2022-human">
<titleInfo>
<title>Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huiyuan</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiali</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd 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">Maja</namePart>
<namePart type="family">Popović</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">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human judgement. We focus on the task of formality transfer, and on the three aspects that are usually evaluated: style strength, content preservation, and fluency. To cast light on how such aspects are assessed by common and new metrics, we run a human-based evaluation and perform a rich correlation analysis. We are then able to offer some recommendations on the use of such metrics in formality transfer, also with an eye to their generalisability (or not) to related tasks.</abstract>
<identifier type="citekey">lai-etal-2022-human</identifier>
<identifier type="doi">10.18653/v1/2022.humeval-1.9</identifier>
<location>
<url>https://aclanthology.org/2022.humeval-1.9</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>102</start>
<end>115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
%A Lai, Huiyuan
%A Mao, Jiali
%A Toral, Antonio
%A Nissim, Malvina
%Y Belz, Anya
%Y Popović, Maja
%Y Reiter, Ehud
%Y Shimorina, Anastasia
%S Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F lai-etal-2022-human
%X Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human judgement. We focus on the task of formality transfer, and on the three aspects that are usually evaluated: style strength, content preservation, and fluency. To cast light on how such aspects are assessed by common and new metrics, we run a human-based evaluation and perform a rich correlation analysis. We are then able to offer some recommendations on the use of such metrics in formality transfer, also with an eye to their generalisability (or not) to related tasks.
%R 10.18653/v1/2022.humeval-1.9
%U https://aclanthology.org/2022.humeval-1.9
%U https://doi.org/10.18653/v1/2022.humeval-1.9
%P 102-115
Markdown (Informal)
[Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer](https://aclanthology.org/2022.humeval-1.9) (Lai et al., HumEval 2022)
ACL