paulhindemith
commited on
Commit
•
3104ae1
1
Parent(s):
bf2baa3
Update README.md
Browse files
README.md
CHANGED
@@ -19,13 +19,6 @@ widget:
|
|
19 |
|
20 |
Pretrained FastText word vector for Japanese
|
21 |
|
22 |
-
## Reference
|
23 |
-
- fastText </br>
|
24 |
-
https://github.com/facebookresearch/fastText
|
25 |
-
|
26 |
-
- word vector data </br>
|
27 |
-
https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ja.300.vec.gz
|
28 |
-
|
29 |
## Usage
|
30 |
|
31 |
Google Colaboratory Example
|
@@ -50,4 +43,11 @@ pd.DataFrame(np.array(pipeline(text)).T, columns=pipeline.tokenizer.tokenize(tex
|
|
50 |
```
|
51 |
pipeline.tokenizer.target_hinshi = ["動詞", "名詞", "形容詞"]
|
52 |
pd.DataFrame(np.array(pipeline(text)).T, columns=pipeline.tokenizer.tokenize(text))
|
53 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
Pretrained FastText word vector for Japanese
|
21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
## Usage
|
23 |
|
24 |
Google Colaboratory Example
|
|
|
43 |
```
|
44 |
pipeline.tokenizer.target_hinshi = ["動詞", "名詞", "形容詞"]
|
45 |
pd.DataFrame(np.array(pipeline(text)).T, columns=pipeline.tokenizer.tokenize(text))
|
46 |
+
```
|
47 |
+
|
48 |
+
## License
|
49 |
+
This model utilizes the folllowing pretrained vectors.
|
50 |
+
Name: fastText
|
51 |
+
Credit: https://fasttext.cc/
|
52 |
+
License: [Creative Commons Attribution-Share-Alike License 3.0](https://creativecommons.org/licenses/by-sa/3.0/)
|
53 |
+
Link: https://dl.fbaipublicfiles.com/fasttext/vectors-wiki/wiki.ja.vec
|