Text Classification with Novelty Detection
It addresses the issue of handling unseen classes in text classification for applications where training data is incomplete, representing an incremental advance over existing methods.
This paper tackles the problem of detecting novel or unexpected instances in text classification, where test data may include classes not seen during training, and proposes a method that converts it to a pair-wise matching problem, achieving substantial improvements over state-of-the-art baselines.
This paper studies the problem of detecting novel or unexpected instances in text classification. In traditional text classification, the classes appeared in testing must have been seen in training. However, in many applications, this is not the case because in testing, we may see unexpected instances that are not from any of the training classes. In this paper, we propose a significantly more effective approach that converts the original problem to a pair-wise matching problem and then outputs how probable two instances belong to the same class. Under this approach, we present two models. The more effective model uses two embedding matrices of a pair of instances as two channels of a CNN. The output probabilities from such pairs are used to judge whether a test instance is from a seen class or is novel/unexpected. Experimental results show that the proposed method substantially outperforms the state-of-the-art baselines.