Kun Ma
commited on
Commit
·
483feb7
1
Parent(s):
3a533d5
update README
Browse files- README.md +11 -0
- fill-mask-result.png +0 -0
README.md
CHANGED
@@ -33,5 +33,16 @@ Available models include:
|
|
33 |
* [`SecBERT`](https://huggingface.co/jackaduma/SecBERT)
|
34 |
* [`SecRoBERTa`](https://huggingface.co/jackaduma/SecRoBERTa)
|
35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
|
37 |
The original repo can be found [here](https://github.com/jackaduma/SecBERT).
|
|
|
33 |
* [`SecBERT`](https://huggingface.co/jackaduma/SecBERT)
|
34 |
* [`SecRoBERTa`](https://huggingface.co/jackaduma/SecRoBERTa)
|
35 |
|
36 |
+
---
|
37 |
+
## **Fill Mask**
|
38 |
+
|
39 |
+
We proposed to build language model which work on cyber security text, as result, it can improve downstream tasks (NER, Text Classification, Semantic Understand, Q&A) in Cyber Security Domain.
|
40 |
+
|
41 |
+
First, as below shows Fill-Mask pipeline in [Google Bert](), [AllenAI SciBert](https://github.com/allenai/scibert) and our [SecBERT](https://github.com/jackaduma/SecBERT) .
|
42 |
+
|
43 |
+
|
44 |
+
<img src="./fill-mask-result.png" width="150%" height="150%">
|
45 |
+
|
46 |
+
---
|
47 |
|
48 |
The original repo can be found [here](https://github.com/jackaduma/SecBERT).
|
fill-mask-result.png
ADDED