TIER-A: Denoising Learning Framework for Information Extraction
This work addresses overfitting in information extraction for NLP practitioners, offering an incremental improvement through a novel regularization method.
The paper tackles the problem of deep learning models overfitting on noisy data in information extraction by proposing TIER-A, a co-regularization joint-training framework that uses temperature calibration and information entropy regularization, achieving improved performance on noisy datasets like TACRED and CoNLL03.
With the development of deep neural language models, great progress has been made in information extraction recently. However, deep learning models often overfit on noisy data points, leading to poor performance. In this work, we examine the role of information entropy in the overfitting process and draw a key insight that overfitting is a process of overconfidence and entropy decreasing. Motivated by such properties, we propose a simple yet effective co-regularization joint-training framework TIER-A, Aggregation Joint-training Framework with Temperature Calibration and Information Entropy Regularization. Our framework consists of several neural models with identical structures. These models are jointly trained and we avoid overfitting by introducing temperature and information entropy regularization. Extensive experiments on two widely-used but noisy datasets, TACRED and CoNLL03, demonstrate the correctness of our assumption and the effectiveness of our framework.