Iterated dilated convolutional neural networks for word segmentation
Han He, Xiaokun Yang, Lei Wu, Guan Wang · Neural Network World · 2020
The latest development of neural word segmentation is governed by bi-directional Long Short-Term Memory Networks (Bi-LSTMs) that utilize Recurrent Neural Networks (RNNs) as standard sequence tagging models, resulting in expressive and accurate performance on large-scale dataset.However, RNNs are not adapted to fully exploit the parallelism capability of Graphics Processing Unit (GPU), limiting their computational efficiency in both learning and inferring phases.This paper proposes a novel approach adopting Iterated Dilated Convolutional Neural Networks (ID-CNNs) to supersede Bi-LSTMs for faster computation while retaining accuracy.Our implementation has achieved state-of-the-art result on SIGHAN Bakeoff 2005 datasets.Extensive experiments showed that our approach with ID-CNNs enables 3× training time speedups with no accuracy loss, achieving better accuracy compared to the prevailing Bi-LSTMs.Source code and corpora of this paper have been made publicly available on GitHub 1 .