BriefGPT.xyz
Jul, 2019
自我关注网络在中文分词中的应用研究
Investigating Self-Attention Network for Chinese Word Segmentation
HTML
PDF
Leilei Gan, Yue Zhang
TL;DR
研究了自注意网络和BERT对中文分词任务的影响，提出了将词信息集成到自注意网络中的方法，并展示了该方法在6个领域基准测试中的最佳结果。
Abstract
neural network
has become the dominant method for
chinese word segmentation
. Most existing models cast the task as sequence labeling, using BiLSTM-CRF for representing the input and making output predictions. Rec
→