@inproceedings{-ekbal-2022-adversarial,
title = "Adversarial Sample Generation for Aspect based Sentiment Classification",
author = "{Mamta} and
Ekbal, Asif",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.44",
doi = "10.18653/v1/2022.findings-aacl.44",
pages = "478--492",
abstract = "Deep learning models have been proven vulnerable towards small imperceptible perturbed input, known as adversarial samples, which are indiscernible by humans. Initial attacks in Natural Language Processing perturb characters or words in sentences using heuristics and synonyms-based strategies, resulting in grammatical incorrect or out-of-context sentences. Recent works attempt to generate contextual adversarial samples using a masked language model, capturing word relevance using leave-one-out (LOO). However, they lack the design to maintain the semantic coherency for aspect based sentiment analysis (ABSA) tasks. Moreover, they focused on resource-rich languages like English. We present an attack algorithm for the ABSA task by exploiting model explainability techniques to address these limitations. It does not require access to the training data, raw access to the model, or calibrating a new model. Our proposed method generates adversarial samples for a given aspect, maintaining more semantic coherency. In addition, it can be generalized to low-resource languages, which are at high risk due to resource scarcity. We show the effectiveness of the proposed attack using automatic and human evaluation. Our method outperforms the state-of-art methods in perturbation ratio, success rate, and semantic coherence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="-ekbal-2022-adversarial">
<titleInfo>
<title>Adversarial Sample Generation for Aspect based Sentiment Classification</title>
</titleInfo>
<name>
<namePart>Mamta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep learning models have been proven vulnerable towards small imperceptible perturbed input, known as adversarial samples, which are indiscernible by humans. Initial attacks in Natural Language Processing perturb characters or words in sentences using heuristics and synonyms-based strategies, resulting in grammatical incorrect or out-of-context sentences. Recent works attempt to generate contextual adversarial samples using a masked language model, capturing word relevance using leave-one-out (LOO). However, they lack the design to maintain the semantic coherency for aspect based sentiment analysis (ABSA) tasks. Moreover, they focused on resource-rich languages like English. We present an attack algorithm for the ABSA task by exploiting model explainability techniques to address these limitations. It does not require access to the training data, raw access to the model, or calibrating a new model. Our proposed method generates adversarial samples for a given aspect, maintaining more semantic coherency. In addition, it can be generalized to low-resource languages, which are at high risk due to resource scarcity. We show the effectiveness of the proposed attack using automatic and human evaluation. Our method outperforms the state-of-art methods in perturbation ratio, success rate, and semantic coherence.</abstract>
<identifier type="citekey">-ekbal-2022-adversarial</identifier>
<identifier type="doi">10.18653/v1/2022.findings-aacl.44</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.44</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>478</start>
<end>492</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarial Sample Generation for Aspect based Sentiment Classification
%A Ekbal, Asif
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%A Mamta
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F -ekbal-2022-adversarial
%X Deep learning models have been proven vulnerable towards small imperceptible perturbed input, known as adversarial samples, which are indiscernible by humans. Initial attacks in Natural Language Processing perturb characters or words in sentences using heuristics and synonyms-based strategies, resulting in grammatical incorrect or out-of-context sentences. Recent works attempt to generate contextual adversarial samples using a masked language model, capturing word relevance using leave-one-out (LOO). However, they lack the design to maintain the semantic coherency for aspect based sentiment analysis (ABSA) tasks. Moreover, they focused on resource-rich languages like English. We present an attack algorithm for the ABSA task by exploiting model explainability techniques to address these limitations. It does not require access to the training data, raw access to the model, or calibrating a new model. Our proposed method generates adversarial samples for a given aspect, maintaining more semantic coherency. In addition, it can be generalized to low-resource languages, which are at high risk due to resource scarcity. We show the effectiveness of the proposed attack using automatic and human evaluation. Our method outperforms the state-of-art methods in perturbation ratio, success rate, and semantic coherence.
%R 10.18653/v1/2022.findings-aacl.44
%U https://aclanthology.org/2022.findings-aacl.44
%U https://doi.org/10.18653/v1/2022.findings-aacl.44
%P 478-492
Markdown (Informal)
[Adversarial Sample Generation for Aspect based Sentiment Classification](https://aclanthology.org/2022.findings-aacl.44) (Mamta & Ekbal, Findings 2022)
ACL