BriefGPT.xyz
Apr, 2020
使用BERT统一多准则中文分词
Unified Multi-Criteria Chinese Word Segmentation with BERT
HTML
PDF
Zhen Ke, Liang Shi, Erli Meng, Bin Wang, Xipeng Qiu...
TL;DR
本文利用预训练Bert模型和bigram特征,提出了一个新的基于Bert的统一的MCCWS模型并加入了一个辅助分类任务,在8个具有不同标准的数据集上进行实验,并取得了新的最优结果。
Abstract
Multi-Criteria
chinese word segmentation
(
mccws
) aims at finding word boundaries in a Chinese sentence composed of continuous characters while multiple segmentation criteria exist. The unified framework has been
→