@inproceedings{lepekhin-sharoff-2022-estimating,
title = "Estimating Confidence of Predictions of Individual Classifiers and {T}heir{E}nsembles for the Genre Classification Task",
author = "Lepekhin, Mikhail and
Sharoff, Serge",
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-1.642",
pages = "5974--5982",
abstract = "Genre identification is a kind of non-topic text classification. The main difference between this task and topic classification is that genre, unlike topic, usually cannot be expressed just by some keywords and is defined as a functional space. Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification. However, in many cases, their downstream application to very large corpora, such as those extracted from social media, can lead to unreliable results because of dataset shifts, when some raw texts do not match the profile of the training set. To mitigate this problem, we experiment with individual models as well as with their ensembles. To evaluate the robustness of all models we use a prediction confidence metric, which estimates the reliability of a prediction in the absence of a gold standard label. We can evaluate robustness via the confidence gap between the correctly classified texts and the misclassified ones on a labeled test corpus, higher gaps make it easier to identify whether a text is classified correctly. Our results show that for all of the classifiers tested in this study, there is a confidence gap, but for the ensembles, the gap is wider, meaning that ensembles are more robust than their individual models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lepekhin-sharoff-2022-estimating">
<titleInfo>
<title>Estimating Confidence of Predictions of Individual Classifiers and TheirEnsembles for the Genre Classification Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Lepekhin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</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>Genre identification is a kind of non-topic text classification. The main difference between this task and topic classification is that genre, unlike topic, usually cannot be expressed just by some keywords and is defined as a functional space. Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification. However, in many cases, their downstream application to very large corpora, such as those extracted from social media, can lead to unreliable results because of dataset shifts, when some raw texts do not match the profile of the training set. To mitigate this problem, we experiment with individual models as well as with their ensembles. To evaluate the robustness of all models we use a prediction confidence metric, which estimates the reliability of a prediction in the absence of a gold standard label. We can evaluate robustness via the confidence gap between the correctly classified texts and the misclassified ones on a labeled test corpus, higher gaps make it easier to identify whether a text is classified correctly. Our results show that for all of the classifiers tested in this study, there is a confidence gap, but for the ensembles, the gap is wider, meaning that ensembles are more robust than their individual models.</abstract>
<identifier type="citekey">lepekhin-sharoff-2022-estimating</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.642</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5974</start>
<end>5982</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Estimating Confidence of Predictions of Individual Classifiers and TheirEnsembles for the Genre Classification Task
%A Lepekhin, Mikhail
%A Sharoff, Serge
%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 lepekhin-sharoff-2022-estimating
%X Genre identification is a kind of non-topic text classification. The main difference between this task and topic classification is that genre, unlike topic, usually cannot be expressed just by some keywords and is defined as a functional space. Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification. However, in many cases, their downstream application to very large corpora, such as those extracted from social media, can lead to unreliable results because of dataset shifts, when some raw texts do not match the profile of the training set. To mitigate this problem, we experiment with individual models as well as with their ensembles. To evaluate the robustness of all models we use a prediction confidence metric, which estimates the reliability of a prediction in the absence of a gold standard label. We can evaluate robustness via the confidence gap between the correctly classified texts and the misclassified ones on a labeled test corpus, higher gaps make it easier to identify whether a text is classified correctly. Our results show that for all of the classifiers tested in this study, there is a confidence gap, but for the ensembles, the gap is wider, meaning that ensembles are more robust than their individual models.
%U https://aclanthology.org/2022.lrec-1.642
%P 5974-5982
Markdown (Informal)
[Estimating Confidence of Predictions of Individual Classifiers and TheirEnsembles for the Genre Classification Task](https://aclanthology.org/2022.lrec-1.642) (Lepekhin & Sharoff, LREC 2022)
ACL