ODIST: Open World Classification via Distributionally Shifted Instances Authors

Lei Shu, Yassine Benajiba, Saab Mansour, Yi Zhang

Abstract: In this work, we address the open-world classification problem with a method called ODIST (open-world classification via distributionally shifted instances). This novel and straightforward method can create out-of-domain instances from the in-domain training examples with the help of a pre-trained language model. Experimental results show that ODIST performs better than the state-of-the-art decision boundary finding method.