@inproceedings{antonio-rodrigues-etal-2020-reproduction,
title = "Reproduction and Revival of the Argument Reasoning Comprehension Task",
author = "Ant{\'o}nio Rodrigues, Jo{\~a}o and
Branco, Ruben and
Silva, Jo{\~a}o and
Branco, Ant{\'o}nio",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.622",
pages = "5055--5064",
abstract = "Reproduction of scientific findings is essential for scientific development across all scientific disciplines and reproducing results of previous works is a basic requirement for validating the hypothesis and conclusions put forward by them. This paper reports on the scientific reproduction of several systems addressing the Argument Reasoning Comprehension Task of SemEval2018. Given a recent publication that pointed out spurious statistical cues in the data set used in the shared task, and that produced a revised version of it, we also evaluated the reproduced systems with this new data set. The exercise reported here shows that, in general, the reproduction of these systems is successful with scores in line with those reported in SemEval2018. However, the performance scores are worst than those, and even below the random baseline, when the reproduced systems are run over the revised data set expunged from data artifacts. This demonstrates that this task is actually a much harder challenge than what could have been perceived from the inflated, close to human-level performance scores obtained with the data set used in SemEval2018. This calls for a revival of this task as there is much room for improvement until systems may come close to the upper bound provided by human performance.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antonio-rodrigues-etal-2020-reproduction">
<titleInfo>
<title>Reproduction and Revival of the Argument Reasoning Comprehension Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">António Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruben</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Reproduction of scientific findings is essential for scientific development across all scientific disciplines and reproducing results of previous works is a basic requirement for validating the hypothesis and conclusions put forward by them. This paper reports on the scientific reproduction of several systems addressing the Argument Reasoning Comprehension Task of SemEval2018. Given a recent publication that pointed out spurious statistical cues in the data set used in the shared task, and that produced a revised version of it, we also evaluated the reproduced systems with this new data set. The exercise reported here shows that, in general, the reproduction of these systems is successful with scores in line with those reported in SemEval2018. However, the performance scores are worst than those, and even below the random baseline, when the reproduced systems are run over the revised data set expunged from data artifacts. This demonstrates that this task is actually a much harder challenge than what could have been perceived from the inflated, close to human-level performance scores obtained with the data set used in SemEval2018. This calls for a revival of this task as there is much room for improvement until systems may come close to the upper bound provided by human performance.</abstract>
<identifier type="citekey">antonio-rodrigues-etal-2020-reproduction</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.622</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5055</start>
<end>5064</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reproduction and Revival of the Argument Reasoning Comprehension Task
%A António Rodrigues, João
%A Branco, Ruben
%A Silva, João
%A Branco, António
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F antonio-rodrigues-etal-2020-reproduction
%X Reproduction of scientific findings is essential for scientific development across all scientific disciplines and reproducing results of previous works is a basic requirement for validating the hypothesis and conclusions put forward by them. This paper reports on the scientific reproduction of several systems addressing the Argument Reasoning Comprehension Task of SemEval2018. Given a recent publication that pointed out spurious statistical cues in the data set used in the shared task, and that produced a revised version of it, we also evaluated the reproduced systems with this new data set. The exercise reported here shows that, in general, the reproduction of these systems is successful with scores in line with those reported in SemEval2018. However, the performance scores are worst than those, and even below the random baseline, when the reproduced systems are run over the revised data set expunged from data artifacts. This demonstrates that this task is actually a much harder challenge than what could have been perceived from the inflated, close to human-level performance scores obtained with the data set used in SemEval2018. This calls for a revival of this task as there is much room for improvement until systems may come close to the upper bound provided by human performance.
%U https://aclanthology.org/2020.lrec-1.622
%P 5055-5064
Markdown (Informal)
[Reproduction and Revival of the Argument Reasoning Comprehension Task](https://aclanthology.org/2020.lrec-1.622) (António Rodrigues et al., LREC 2020)
ACL