jannikskytt
commited on
Commit
•
40688e3
1
Parent(s):
5108780
Update README.md
Browse files
README.md
CHANGED
@@ -4,5 +4,7 @@ license: cc-by-nc-3.0
|
|
4 |
# Danish medical word embeddings
|
5 |
|
6 |
MeDa-We was trained on a Danish medical corpus of 123M tokens. The word embeddings are 300-dimensional and are trained using [FastText](https://fasttext.cc/).
|
|
|
7 |
The embeddings were trained for 10 epochs using a window size of 5 and 10 negative samples.
|
8 |
-
|
|
|
|
4 |
# Danish medical word embeddings
|
5 |
|
6 |
MeDa-We was trained on a Danish medical corpus of 123M tokens. The word embeddings are 300-dimensional and are trained using [FastText](https://fasttext.cc/).
|
7 |
+
|
8 |
The embeddings were trained for 10 epochs using a window size of 5 and 10 negative samples.
|
9 |
+
|
10 |
+
The development of the corpus and word embeddings is described further in our [paper](https://openreview.net/forum?id=cc9USd2ec-)
|