Commit
·
0f4ac77
1
Parent(s):
b3e2c70
base_model
Browse files
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags:
|
|
| 6 |
- "token-classification"
|
| 7 |
- "pos"
|
| 8 |
- "dependency-parsing"
|
|
|
|
| 9 |
datasets:
|
| 10 |
- "universal_dependencies"
|
| 11 |
license: "apache-2.0"
|
|
@@ -19,7 +20,7 @@ widget:
|
|
| 19 |
|
| 20 |
## Model Description
|
| 21 |
|
| 22 |
-
This is a
|
| 23 |
|
| 24 |
## How to Use
|
| 25 |
|
|
|
|
| 6 |
- "token-classification"
|
| 7 |
- "pos"
|
| 8 |
- "dependency-parsing"
|
| 9 |
+
base_model: team-lucid/deberta-v3-base-korean
|
| 10 |
datasets:
|
| 11 |
- "universal_dependencies"
|
| 12 |
license: "apache-2.0"
|
|
|
|
| 20 |
|
| 21 |
## Model Description
|
| 22 |
|
| 23 |
+
This is a DeBERTa(V2) model pre-trained on Korean texts for POS-tagging and dependency-parsing, derived from [deberta-v3-base-korean](https://huggingface.co/team-lucid/deberta-v3-base-korean) and [morphUD-korean](https://github.com/jungyeul/morphUD-korean). Every morpheme (형태소) is tagged by [UPOS](https://universaldependencies.org/u/pos/)(Universal Part-Of-Speech).
|
| 24 |
|
| 25 |
## How to Use
|
| 26 |
|