2 code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Leo Horne, Matthias Matti, Pouya Pourjafar, Zuowen Wang
In this work, we introduce a GRU-based architecture called GRUBERT that learns to map the different BERT hidden layers to fused embeddings with the aim of achieving high accuracy on the Twitter sentiment analysis task.
1 code implementation • 4 Apr 2020 • Zuowen Wang, Leo Horne
Recent work has put forth the hypothesis that adversarial vulnerabilities in neural networks are due to them overusing "non-robust features" inherent in the training data.