@inproceedings{zhang-etal-2022-experimental,
title = "How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models?",
author = "Zhang, Xiaohan and
Wang, Shaonan and
Zong, Chengqing",
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-1.687/",
pages = "6397--6404",
abstract = "Recent years have witnessed the tendency of neural encoding models on exploring brain language processing using naturalistic stimuli. Neural encoding models are data-driven methods that require an encoding model to investigate the mystery of brain mechanisms hidden in the data. As a data-driven method, the performance of encoding models is very sensitive to the experimental setting. However, it is unknown how the experimental setting further affects the conclusions of neural encoding models. This paper systematically investigated this problem and evaluated the influence of three experimental settings, i.e., the data size, the cross-validation training method, and the statistical testing method. Results demonstrate that inappropriate cross-validation training and small data size can substantially decrease the performance of encoding models, especially in the temporal lobe and the frontal lobe. And different null hypotheses in significance testing lead to highly different significant brain regions. Based on these results, we suggest a block-wise cross-validation training method and an adequate data size for increasing the performance of linear encoding models. We also propose two strict null hypotheses to control false positive discovery rates."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-experimental">
<titleInfo>
<title>How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaohan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaonan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</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>Recent years have witnessed the tendency of neural encoding models on exploring brain language processing using naturalistic stimuli. Neural encoding models are data-driven methods that require an encoding model to investigate the mystery of brain mechanisms hidden in the data. As a data-driven method, the performance of encoding models is very sensitive to the experimental setting. However, it is unknown how the experimental setting further affects the conclusions of neural encoding models. This paper systematically investigated this problem and evaluated the influence of three experimental settings, i.e., the data size, the cross-validation training method, and the statistical testing method. Results demonstrate that inappropriate cross-validation training and small data size can substantially decrease the performance of encoding models, especially in the temporal lobe and the frontal lobe. And different null hypotheses in significance testing lead to highly different significant brain regions. Based on these results, we suggest a block-wise cross-validation training method and an adequate data size for increasing the performance of linear encoding models. We also propose two strict null hypotheses to control false positive discovery rates.</abstract>
<identifier type="citekey">zhang-etal-2022-experimental</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.687/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6397</start>
<end>6404</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models?
%A Zhang, Xiaohan
%A Wang, Shaonan
%A Zong, Chengqing
%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 zhang-etal-2022-experimental
%X Recent years have witnessed the tendency of neural encoding models on exploring brain language processing using naturalistic stimuli. Neural encoding models are data-driven methods that require an encoding model to investigate the mystery of brain mechanisms hidden in the data. As a data-driven method, the performance of encoding models is very sensitive to the experimental setting. However, it is unknown how the experimental setting further affects the conclusions of neural encoding models. This paper systematically investigated this problem and evaluated the influence of three experimental settings, i.e., the data size, the cross-validation training method, and the statistical testing method. Results demonstrate that inappropriate cross-validation training and small data size can substantially decrease the performance of encoding models, especially in the temporal lobe and the frontal lobe. And different null hypotheses in significance testing lead to highly different significant brain regions. Based on these results, we suggest a block-wise cross-validation training method and an adequate data size for increasing the performance of linear encoding models. We also propose two strict null hypotheses to control false positive discovery rates.
%U https://aclanthology.org/2022.lrec-1.687/
%P 6397-6404
Markdown (Informal)
[How Does the Experimental Setting Affect the Conclusions of Neural Encoding Models?](https://aclanthology.org/2022.lrec-1.687/) (Zhang et al., LREC 2022)
ACL