Actor-Critic Network for Q&A in an Adversarial Environment

TL;DR

This paper proposes an actor-critic network approach that combines adversarial data generation and robustness training in NLP question-answering systems, showing promising results against adversarial attacks.

Contribution

It introduces a novel reinforcement learning-inspired framework that jointly trains a critic model to enhance robustness in Q&A models against adversarial attacks.

Findings

Improved robustness against adversarial examples

Effective use of Adversarial SQuAD dataset

Potential for reinforcement learning in NLP robustness

Abstract

Significant work has been placed in the Q&A NLP space to build models that are more robust to adversarial attacks. Two key areas of focus are in generating adversarial data for the purposes of training against these situations or modifying existing architectures to build robustness within. This paper introduces an approach that joins these two ideas together to train a critic model for use in an almost reinforcement learning framework. Using the Adversarial SQuAD "Add One Sent" dataset we show that there are some promising signs for this method in protecting against Adversarial attacks.