Adaptive Scaling for Sparse Detection in Information Extraction

by   Hongyu Lin, et al.

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.


page 1

page 2

page 3

page 4


PIGMIL: Positive Instance Detection via Graph Updating for Multiple Instance Learning

Positive instance detection, especially for these in positive bags (true...

A Comparison of Handcrafted and Deep Neural Network Feature Extraction for Classifying Optical Coherence Tomography (OCT) Images

Optical Coherence Tomography allows ophthalmologist to obtain cross-sect...

Scaling and bias codes for modeling speaker-adaptive DNN-based speech synthesis systems

Most neural-network based speaker-adaptive acoustic models for speech sy...

Neural Network based End-to-End Query by Example Spoken Term Detection

This paper focuses on the problem of query by example spoken term detect...

An Enhanced SCMA Detector Enabled by Deep Neural Network

In this paper, we propose a learning approach for sparse code multiple a...

Almost Surely Stable Deep Dynamics

We introduce a method for learning provably stable deep neural network b...

Memory Aware Synapses: Learning what (not) to forget

Humans can learn in a continuous manner. Old rarely utilized knowledge c...