marksverdhei
commited on
Commit
•
1c28825
1
Parent(s):
252772f
Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ Bag Of Words (BOW) is a simple and typical encoding for making statistical model
|
|
12 |
However BOW is a lossy compression that eliminates a very important feature of text: order
|
13 |
|
14 |
This model is trained to learn the most probable order of an unordered token sequence,
|
15 |
-
using a subset of the c4 dataset.
|
16 |
|
17 |
Currently, it is not very good. I might re-train on a larger subset of c4 later.
|
18 |
|
|
|
12 |
However BOW is a lossy compression that eliminates a very important feature of text: order
|
13 |
|
14 |
This model is trained to learn the most probable order of an unordered token sequence,
|
15 |
+
using a subset of the c4 dataset, and can thus be seen as a "bag-of-words decoder".
|
16 |
|
17 |
Currently, it is not very good. I might re-train on a larger subset of c4 later.
|
18 |
|