Update README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,14 @@ datasets:
|
|
| 14 |
|
| 15 |
This is the pretrained model presented in [SecBERT: A Pretrained Language Model for Cyber Security Text](https://github.com/jackaduma/SecBERT/), which is a BERT model trained on cyber security text.
|
| 16 |
|
| 17 |
-
The training corpus was papers taken from
|
| 18 |
-
|
| 19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
Available models include:
|
| 22 |
* `SecBERT`
|
|
|
|
| 14 |
|
| 15 |
This is the pretrained model presented in [SecBERT: A Pretrained Language Model for Cyber Security Text](https://github.com/jackaduma/SecBERT/), which is a BERT model trained on cyber security text.
|
| 16 |
|
| 17 |
+
The training corpus was papers taken from
|
| 18 |
+
* [APTnotes](https://github.com/kbandla/APTnotes)
|
| 19 |
+
* [Stucco-Data: Cyber security data sources](https://stucco.github.io/data/)
|
| 20 |
+
* [CASIE: Extracting Cybersecurity Event Information from Text](https://ebiquity.umbc.edu/_file_directory_/papers/943.pdf)
|
| 21 |
+
* [SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using Natural Language Processing (SecureNLP)](https://competitions.codalab.org/competitions/17262).
|
| 22 |
+
|
| 23 |
+
SecBERT has its own wordpiece vocabulary (secvocab) that's built to best match the training corpus. We trained [BERT](https://huggingface.co/jackaduma/SecBERT) and
|
| 24 |
+
[SecRoBERTa](https://huggingface.co/jackaduma/SecRoBERTa) versions.
|
| 25 |
|
| 26 |
Available models include:
|
| 27 |
* `SecBERT`
|