Commit
•
a1c969e
1
Parent(s):
323eaa8
Update README.md
Browse files
README.md
CHANGED
|
@@ -1 +1,11 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# GysBERT v1
|
| 2 |
+
|
| 3 |
+
This model is a Historical Language Model for Dutch coming from the [MacBERTh project](https://macberth.netlify.app/).
|
| 4 |
+
|
| 5 |
+
The architecture is based on BERT base uncased from the original BERT pre-training codebase.
|
| 6 |
+
The training material comes mostly from the DBNL and the Delpher newspaper dump.
|
| 7 |
+
The details can be found in the accompanying publication: [Non-Parametric Word Sense Disambiguation for Historical Languages](https://aclanthology.org/2022.nlp4dh-1.16.pdf)
|
| 8 |
+
|
| 9 |
+
The model has been successfully tested on Word Sense Disambiguation tasks as discussed in the referenced paper above.
|
| 10 |
+
|
| 11 |
+
An updated version with an enlarged pre-training dataset is due soon.
|