TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

29 Apr 2020 John X. Morris Eli Lifland Jin Yong Yoo Jake Grigsby Di Jin Yanjun Qi

While there has been substantial research using adversarial attacks to analyze NLP models, each attack is implemented in its own code repository. It remains challenging to develop NLP attacks and utilize them to improve model performance... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Layer Normalization
Normalization
Scaled Dot-Product Attention
Attention Mechanisms
Dense Connections
Feedforward Networks
Residual Connection
Skip Connections
Adam
Stochastic Optimization
Multi-Head Attention
Attention Modules
Attention Dropout
Regularization
Dropout
Regularization
WordPiece
Subword Segmentation
Weight Decay
Regularization
GELU
Activation Functions
Linear Warmup With Linear Decay
Learning Rate Schedules
Softmax
Output Functions
BERT
Language Models