BIBI System Description: Building with CNNs and Breaking with Deep Reinforcement Learning
Yitong Li, Trevor Cohn, Timothy J. Baldwin · 2017
This paper describes our submission to the sentiment analysis sub-task of "Build It, Break It: The Language Edition (BIBI)", on both the builder and breaker sides.As a builder, we use convolutional neural nets, trained on both phrase and sentence data.As a breaker, we use Q-learning to learn minimal change pairs, and apply a token substitution method automatically.We analyse the results to gauge the robustness of NLP systems.