Adaptive Scaling for Sparse Detection in Information Extraction
This addresses a specific bottleneck in information extraction for researchers and practitioners, but appears incremental as it builds on existing cost-sensitive learning approaches.
The paper tackles the problem of neural network detection models performing poorly when positive instances are sparse in information extraction tasks, proposing an adaptive scaling algorithm that directly optimizes F-measure through dynamic cost-sensitive learning, resulting in more effective and stable training.
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 cost-sensitive learning. To this end, we borrow the idea of marginal utility from economics and propose a theoretical framework for instance importance measuring without introducing any additional hyper-parameters. Experiments show that our algorithm leads to a more effective and stable training of neural network based detection models.