@inproceedings{kanashiro-pereira-2022-attention,
title = "Attention-Focused Adversarial Training for Robust Temporal Reasoning",
author = "Kanashiro Pereira, Lis",
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-1.800",
pages = "7352--7359",
abstract = "We propose an enhanced adversarial training algorithm for fine-tuning transformer-based language models (i.e., RoBERTa) and apply it to the temporal reasoning task. Current adversarial training approaches for NLP add the adversarial perturbation only to the embedding layer, ignoring the other layers of the model, which might limit the generalization power of adversarial training. Instead, our algorithm searches for the best combination of layers to add the adversarial perturbation. We add the adversarial perturbation to multiple hidden states or attention representations of the model layers. Adding the perturbation to the attention representations performed best in our experiments. Our model can improve performance on several temporal reasoning benchmarks, and establishes new state-of-the-art results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanashiro-pereira-2022-attention">
<titleInfo>
<title>Attention-Focused Adversarial Training for Robust Temporal Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lis</namePart>
<namePart type="family">Kanashiro Pereira</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>We propose an enhanced adversarial training algorithm for fine-tuning transformer-based language models (i.e., RoBERTa) and apply it to the temporal reasoning task. Current adversarial training approaches for NLP add the adversarial perturbation only to the embedding layer, ignoring the other layers of the model, which might limit the generalization power of adversarial training. Instead, our algorithm searches for the best combination of layers to add the adversarial perturbation. We add the adversarial perturbation to multiple hidden states or attention representations of the model layers. Adding the perturbation to the attention representations performed best in our experiments. Our model can improve performance on several temporal reasoning benchmarks, and establishes new state-of-the-art results.</abstract>
<identifier type="citekey">kanashiro-pereira-2022-attention</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.800</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7352</start>
<end>7359</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attention-Focused Adversarial Training for Robust Temporal Reasoning
%A Kanashiro Pereira, Lis
%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 kanashiro-pereira-2022-attention
%X We propose an enhanced adversarial training algorithm for fine-tuning transformer-based language models (i.e., RoBERTa) and apply it to the temporal reasoning task. Current adversarial training approaches for NLP add the adversarial perturbation only to the embedding layer, ignoring the other layers of the model, which might limit the generalization power of adversarial training. Instead, our algorithm searches for the best combination of layers to add the adversarial perturbation. We add the adversarial perturbation to multiple hidden states or attention representations of the model layers. Adding the perturbation to the attention representations performed best in our experiments. Our model can improve performance on several temporal reasoning benchmarks, and establishes new state-of-the-art results.
%U https://aclanthology.org/2022.lrec-1.800
%P 7352-7359
Markdown (Informal)
[Attention-Focused Adversarial Training for Robust Temporal Reasoning](https://aclanthology.org/2022.lrec-1.800) (Kanashiro Pereira, LREC 2022)
ACL