Commit
•
5a725d3
1
Parent(s):
3fdd67d
Update README.md
Browse files
README.md
CHANGED
@@ -13,16 +13,18 @@ _name_ is pre-trained word vectors for the Ukrainian language, trained with fast
|
|
13 |
|
14 |
Our model increases Accuracy by 6.3% compared to the [Facebook Ukrainian word vectors](https://fasttext.cc/docs/en/crawl-vectors.html) on the word analogy task. The dataset for Ukrainian word analogy is available [here](https://github.com/lang-uk/vecs/).
|
15 |
|
16 |
-
Extrinsic evaluations were performed on two sequence labeling tasks: NER and POS tagging. NER-UK dataset was released by the lang-uk, and Ukrainian (UD) corpus was developed by a non-profit organization Institute for Ukrainian.
|
17 |
|
18 |
Results:
|
19 |
-
1) spaCy NER F-score 0.818
|
20 |
-
2) POS Flair Accuracy 0.824
|
21 |
-
3) POS spaCy Accuracy 0.911
|
22 |
|
23 |
Usage
|
24 |
```
|
25 |
import fasttext.util
|
26 |
-
ft = fasttext.load_model('
|
27 |
ft.get_word_vector('hello')
|
28 |
```
|
|
|
|
|
|
13 |
|
14 |
Our model increases Accuracy by 6.3% compared to the [Facebook Ukrainian word vectors](https://fasttext.cc/docs/en/crawl-vectors.html) on the word analogy task. The dataset for Ukrainian word analogy is available [here](https://github.com/lang-uk/vecs/).
|
15 |
|
16 |
+
Extrinsic evaluations were performed on two sequence labeling tasks: NER and POS tagging. [NER-UK dataset](https://github.com/lang-uk/ner-uk) was released by the [lang-uk](https://lang.org.ua/), and [Ukrainian (UD) corpus](https://github.com/brown-uk/corpus) was developed by a [non-profit organization Institute for Ukrainian](https://mova.institute/).
|
17 |
|
18 |
Results:
|
19 |
+
1) spaCy NER F-score: **0.818**
|
20 |
+
2) POS Flair Accuracy: **0.824**
|
21 |
+
3) POS spaCy Accuracy: **0.911**
|
22 |
|
23 |
Usage
|
24 |
```
|
25 |
import fasttext.util
|
26 |
+
ft = fasttext.load_model('skipgram.uk.300.bin')
|
27 |
ft.get_word_vector('hello')
|
28 |
```
|
29 |
+
|
30 |
+
Copyright: [Dmytro Chaplynskyi](https://twitter.com/dchaplinsky), [lang-uk](https://lang.org.ua) project, Natalya Romanyshyn, (Ukrainian Catholic University)[https://ucu.edu.ua/en/], 2022
|