Downloads · 30 days
11
2% of all-time downloads
x180/macbert4csc-scalarmix-base-chinese
macbert4csc-scalarmix-base-chinese is a fill-mask model from x180. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
11
2% of all-time downloads
All-time downloads
609
Public
Repo size
818 MB
Likes
1
Public
Click a slice to open those files.
.bin409 MB · 100%
From the Hugging Face model README
基于macbert对mask language model微调,进行错字修改。
这个是在shibing624/macbert4csc-base-chinese的基础上进行修改, 其对应的 源码位置。
可参考shibing624/macbert4csc-base-chinese。
主要改动两个地方:
整体下来错字检测二分类对整体模型效果影响并没有很突出,以及整体模型效果并没有超出原作者多少,所以上传这个代码以及模型更多是为了学习记录与思考。 其以pycorrector eval.py跑出来的结果如下:
corpus数据集:
Sentence Level: acc:0.7200, precision:0.8804, recall:0.6154, f1:0.7244, cost time:5.67 s
sighan2015数据集:
Sentence Level: acc:0.7973, precision:0.8265, recall:0.7459, f1:0.7841, cost time:11.19 s