@inproceedings{mersinias-valvis-2022-mitigating,
title = "Mitigating Dataset Artifacts in Natural Language Inference Through Automatic Contextual Data Augmentation and Learning Optimization",
author = "Mersinias, Michail and
Valvis, Panagiotis",
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-1.45",
pages = "427--435",
abstract = "In recent years, natural language inference has been an emerging research area. In this paper, we present a novel data augmentation technique and combine it with a unique learning procedure for that task. Our so-called automatic contextual data augmentation (acda) method manages to be fully automatic, non-trivially contextual, and computationally efficient at the same time. When compared to established data augmentation methods, it is substantially more computationally efficient and requires no manual annotation by a human expert as they usually do. In order to increase its efficiency, we combine acda with two learning optimization techniques: contrastive learning and a hybrid loss function. The former maximizes the benefit of the supervisory signal generated by acda, while the latter incentivises the model to learn the nuances of the decision boundary. Our combined approach is shown experimentally to provide an effective way for mitigating spurious data correlations within a dataset, called dataset artifacts, and as a result improves performance. Specifically, our experiments verify that acda-boosted pre-trained language models that employ our learning optimization techniques, consistently outperform the respective fine-tuned baseline pre-trained language models across both benchmark datasets and adversarial examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mersinias-valvis-2022-mitigating">
<titleInfo>
<title>Mitigating Dataset Artifacts in Natural Language Inference Through Automatic Contextual Data Augmentation and Learning Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michail</namePart>
<namePart type="family">Mersinias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Panagiotis</namePart>
<namePart type="family">Valvis</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 recent years, natural language inference has been an emerging research area. In this paper, we present a novel data augmentation technique and combine it with a unique learning procedure for that task. Our so-called automatic contextual data augmentation (acda) method manages to be fully automatic, non-trivially contextual, and computationally efficient at the same time. When compared to established data augmentation methods, it is substantially more computationally efficient and requires no manual annotation by a human expert as they usually do. In order to increase its efficiency, we combine acda with two learning optimization techniques: contrastive learning and a hybrid loss function. The former maximizes the benefit of the supervisory signal generated by acda, while the latter incentivises the model to learn the nuances of the decision boundary. Our combined approach is shown experimentally to provide an effective way for mitigating spurious data correlations within a dataset, called dataset artifacts, and as a result improves performance. Specifically, our experiments verify that acda-boosted pre-trained language models that employ our learning optimization techniques, consistently outperform the respective fine-tuned baseline pre-trained language models across both benchmark datasets and adversarial examples.</abstract>
<identifier type="citekey">mersinias-valvis-2022-mitigating</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.45</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>427</start>
<end>435</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Dataset Artifacts in Natural Language Inference Through Automatic Contextual Data Augmentation and Learning Optimization
%A Mersinias, Michail
%A Valvis, Panagiotis
%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 mersinias-valvis-2022-mitigating
%X In recent years, natural language inference has been an emerging research area. In this paper, we present a novel data augmentation technique and combine it with a unique learning procedure for that task. Our so-called automatic contextual data augmentation (acda) method manages to be fully automatic, non-trivially contextual, and computationally efficient at the same time. When compared to established data augmentation methods, it is substantially more computationally efficient and requires no manual annotation by a human expert as they usually do. In order to increase its efficiency, we combine acda with two learning optimization techniques: contrastive learning and a hybrid loss function. The former maximizes the benefit of the supervisory signal generated by acda, while the latter incentivises the model to learn the nuances of the decision boundary. Our combined approach is shown experimentally to provide an effective way for mitigating spurious data correlations within a dataset, called dataset artifacts, and as a result improves performance. Specifically, our experiments verify that acda-boosted pre-trained language models that employ our learning optimization techniques, consistently outperform the respective fine-tuned baseline pre-trained language models across both benchmark datasets and adversarial examples.
%U https://aclanthology.org/2022.lrec-1.45
%P 427-435
Markdown (Informal)
[Mitigating Dataset Artifacts in Natural Language Inference Through Automatic Contextual Data Augmentation and Learning Optimization](https://aclanthology.org/2022.lrec-1.45) (Mersinias & Valvis, LREC 2022)
ACL