paper-with-me

홈 › Papers

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

2019-07-27 · Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness of these models by exposing the maliciously crafted adversarial examples. In this paper, we present TextFooler, a simple but strong baseline to generate natural adversarial text. By applying it to two fundamental natural language tasks, text classification and textual entailment, we successfully attacked three target models, including the powerful pre-trained BERT, and the widely used convolutional and recurrent neural networks. We demonstrate the advantages of this framework in three ways: (1) effective---it outperforms state-of-the-art attacks in terms of success rate and perturbation rate, (2) utility-preserving---it preserves semantic content and grammaticality, and remains correctly classified by humans, and (3) efficient---it generates adversarial text with computational complexity linear to the text length. *The code, pre-trained target models, and test examples are available at https://github.com/jind11/TextFooler.

📄 PDF Abstract BibTeX arXiv:1907.11932

Code (7)

jind11/TextFooler 공식 구현 pytorch
DAI-Lab/fibber tf
Jason-J-Choi/DeBERTa_TxtClassifier pytorch
utsjiyaoli/qa-attack pytorch
vincent861223/Train_BERT_With_TextFooler pytorch
wqj111186/TextFooler pytorch
yuehwai0508/Bert_TFL pytorch

Tasks

Adversarial TextGeneral ClassificationNatural Language InferenceText Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

How Fast can BERT Learn Simple Natural Language Inference?

2021-04-01 · EACL 2021 2 · Yi-Chung Lin, Keh-Yih Su

This paper empirically studies whether BERT can really learn to conduct natural language inference (NLI) without utilizing hidden dataset bias; and how efficiently it can learn if it could. This is done via creating a si…

Natural Language Inference

Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Although transformer-based Neural Language Models obtain impressive results on a wide variety of tasks, their generalization abilities are not well understood. They have been shown to perform strongly on subject-verb num…

Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task

2022-04-14 · Findings (ACL) 2022 5 · Karim Lasri, Alessandro Lenci, Thierry Poibeau

Although transformer-based Neural Language Models demonstrate impressive performance on a variety of tasks, their generalization abilities are not well understood. They have been shown to perform strongly on subject-verb…

Exponentially Faster Language Modelling

2023-11-15 · Peter Belcak, Roger Wattenhofer

Language models only really need to use an exponential fraction of their neurons for individual inferences. As proof, we present UltraFastBERT, a BERT variant that uses 0.3% of its neurons during inference while performi…

BenchmarkingCPULanguage Modelling

Multilingual Question Answering from Formatted Text applied to Conversational Agents

2019-10-10 · Wissam Siblini, Charlotte Pasqual, Axel Lavielle, Mohamed Challal 외

Recent advances with language models (e.g. BERT, XLNet, ...), have allowed surpassing human performance on complex NLP tasks such as Reading Comprehension. However, labeled datasets for training are available mostly in E…

Extractive Question-AnsweringMachine TranslationQuestion AnsweringReading Comprehension