@inproceedings{poibeau-2022-human,
title = "On {``}Human Parity{''} and {``}Super Human Performance{''} in Machine Translation Evaluation",
author = "Poibeau, Thierry",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.647",
pages = "6018--6023",
abstract = "In this paper, we reassess claims of human parity and super human performance in machine translation. Although these terms have already been discussed, as well as the evaluation protocols used to achieved these conclusions (human-parity is achieved i) only for a very reduced number of languages, ii) on very specific types of documents and iii) with very literal translations), we show that the terms used are themselves problematic, and that human translation involves much more than what is embedded in automatic systems. We also discuss ethical issues related to the way results are presented and advertised. Finally, we claim that a better assessment of human capacities should be put forward and that the goal of replacing humans by machines is not a desirable one.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poibeau-2022-human">
<titleInfo>
<title>On “Human Parity” and “Super Human Performance” in Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Poibeau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we reassess claims of human parity and super human performance in machine translation. Although these terms have already been discussed, as well as the evaluation protocols used to achieved these conclusions (human-parity is achieved i) only for a very reduced number of languages, ii) on very specific types of documents and iii) with very literal translations), we show that the terms used are themselves problematic, and that human translation involves much more than what is embedded in automatic systems. We also discuss ethical issues related to the way results are presented and advertised. Finally, we claim that a better assessment of human capacities should be put forward and that the goal of replacing humans by machines is not a desirable one.</abstract>
<identifier type="citekey">poibeau-2022-human</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.647</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6018</start>
<end>6023</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On “Human Parity” and “Super Human Performance” in Machine Translation Evaluation
%A Poibeau, Thierry
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F poibeau-2022-human
%X In this paper, we reassess claims of human parity and super human performance in machine translation. Although these terms have already been discussed, as well as the evaluation protocols used to achieved these conclusions (human-parity is achieved i) only for a very reduced number of languages, ii) on very specific types of documents and iii) with very literal translations), we show that the terms used are themselves problematic, and that human translation involves much more than what is embedded in automatic systems. We also discuss ethical issues related to the way results are presented and advertised. Finally, we claim that a better assessment of human capacities should be put forward and that the goal of replacing humans by machines is not a desirable one.
%U https://aclanthology.org/2022.lrec-1.647
%P 6018-6023
Markdown (Informal)
[On “Human Parity” and “Super Human Performance” in Machine Translation Evaluation](https://aclanthology.org/2022.lrec-1.647) (Poibeau, LREC 2022)
ACL