Commit
•
cc3f431
1
Parent(s):
16bb34f
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,11 +2,12 @@
|
|
| 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 |
|
| 7 |
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.
|
| 8 |
-
|
| 9 |
-
|
| 10 |
|
| 11 |
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.
|
| 12 |
|
|
|
|
| 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 |
+
|
| 7 |
|
| 8 |
|
| 9 |
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.
|
| 10 |
+
|
|
|
|
| 11 |
|
| 12 |
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.
|
| 13 |
|