This paper focuses on detection tasks in information extraction, where positive instances are sparsely distributed and models are usually evaluated using F-measure on positive classes. These characteristics often result in deficient performance of neural network based detection models. In this paper, we propose adaptive scaling, an algorithm which can handle the positive sparsity problem and directly optimize over F-measure via dynamic costsensitive learning. To this end, we borrow the idea of

more »

... arginal utility from economics and propose a theoretical framework for instance importance measuring without introducing any additional hyperparameters. Experiments show that our algorithm leads to a more effective and stable training of neural network based detection models.