Why KDAC? A general activation function for knowledge discovery

TL;DR

This paper introduces KDAC, a novel activation function designed to enhance knowledge discovery in deep learning-based named entity recognition by overcoming gradient vanishing and non-differentiability issues.

Contribution

KDAC is a new aggregation activation function with multiple modes that improves gradient flow and representation of latent semantics in DNER models.

Findings

KDAC outperforms existing activation functions on six benchmark datasets.

KDAC enhances the performance of BERT-BiLSTM-CNN-CRF models.

KDAC demonstrates stable and dynamic properties beneficial for knowledge discovery.

Abstract

Deep learning oriented named entity recognition (DNER) has gradually become the paradigm of knowledge discovery, which greatly promotes domain intelligence. However, the current activation function of DNER fails to treat gradient vanishing, no negative output or non-differentiable existence, which may impede knowledge exploration caused by the omission and incomplete representation of latent semantics. To break through the dilemma, we present a novel activation function termed KDAC. Detailly, KDAC is an aggregation function with multiple conversion modes. The backbone of the activation region is the interaction between exponent and linearity, and the both ends extend through adaptive linear divergence, which surmounts the obstacle of gradient vanishing and no negative output. Crucially, the non-differentiable points are alerted and eliminated by an approximate smoothing algorithm. KDAC has a series of brilliant properties, including nonlinear, stable near-linear transformation and derivative, as well as dynamic style, etc. We perform experiments based on BERT-BiLSTM-CNN-CRF model on six benchmark datasets containing different domain knowledge, such as Weibo, Clinical, E-commerce, Resume, HAZOP and People's daily. The evaluation results show that KDAC is advanced and effective, and can provide more generalized activation to stimulate the performance of DNER. We hope that KDAC can be exploited as a promising activation function to devote itself to the construction of knowledge.