Commit
•
0fb9b92
1
Parent(s):
fc0be57
dependency-parsing
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ widget:
|
|
17 |
|
18 |
## Model Description
|
19 |
|
20 |
-
This is a GPT-2 model for POS-tagging, derived from [gpt2-small-japanese-char](https://huggingface.co/ku-nlp/gpt2-small-japanese-char). Every short-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
|
21 |
|
22 |
## How to Use
|
23 |
|
@@ -27,3 +27,15 @@ nlp=pipeline("upos","KoichiYasuoka/gpt2-small-japanese-upos",trust_remote_code=T
|
|
27 |
print(nlp("国境の長いトンネルを抜けると雪国であった。"))
|
28 |
```
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model Description
|
19 |
|
20 |
+
This is a GPT-2 model for POS-tagging and dependency-parsing, derived from [gpt2-small-japanese-char](https://huggingface.co/ku-nlp/gpt2-small-japanese-char). Every short-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
|
21 |
|
22 |
## How to Use
|
23 |
|
|
|
27 |
print(nlp("国境の長いトンネルを抜けると雪国であった。"))
|
28 |
```
|
29 |
|
30 |
+
or
|
31 |
+
|
32 |
+
```py
|
33 |
+
import esupar
|
34 |
+
nlp=esupar.load("KoichiYasuoka/gpt2-small-japanese-upos")
|
35 |
+
print(nlp("国境の長いトンネルを抜けると雪国であった。"))
|
36 |
+
```
|
37 |
+
|
38 |
+
## See Also
|
39 |
+
|
40 |
+
[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models
|
41 |
+
|