Commit
•
a437efa
1
Parent(s):
d728f7a
Update README.md
Browse filesUpdating the first version of readme.
README.md
CHANGED
@@ -1,3 +1,10 @@
|
|
1 |
---
|
2 |
license: afl-3.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: afl-3.0
|
3 |
---
|
4 |
+
This project page is about the pytorch code implementation of GlyphBERT by the HITsz-TMG research group.
|
5 |
+
|
6 |
+
GlyphBERT is a Chinese pre-training model that includes Chinese character glyph features.It renders the input characters into images and designs them in the form of multi-channel location feature maps, and designs a two-layer residual convolutional neural network module to extract the image features of the characters for training.
|
7 |
+
|
8 |
+
The experimental results show that the performance of the pre-training model can be well improved by fusing the features of Chinese glyphs. GlyphBERT is much better than BERT in multiple downstream tasks, and has strong transferability.
|
9 |
+
|
10 |
+
For more details about using it, you can check the [github repo](https://github.com/HITsz-TMG/GlyphBERT)
|