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
|