Update README.md
Browse files
README.md
CHANGED
@@ -37,7 +37,7 @@ results = [{'token': input_tokens[idx],
|
|
37 |
It is perhaps good to note that we assume the [Inside-Outside-Beginning](https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)) format.
|
38 |
|
39 |
## Intended use
|
40 |
-
The model is finetuned for negation detection on Dutch clinical text. Since it is a domain-specific model trained on medical data, it is meant to be used on medical NLP tasks for Dutch. This particular model is trained on a 512-max token windows surrounding the concept-to-be negated.
|
41 |
|
42 |
## Data
|
43 |
The pre-trained model was trained on nearly 10 million hospital notes from the Amsterdam University Medical Centres. The training data was anonymized before starting the pre-training procedure.
|
|
|
37 |
It is perhaps good to note that we assume the [Inside-Outside-Beginning](https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)) format.
|
38 |
|
39 |
## Intended use
|
40 |
+
The model is finetuned for negation detection on Dutch clinical text. Since it is a domain-specific model trained on medical data, it is meant to be used on medical NLP tasks for Dutch. This particular model is trained on a 512-max token windows surrounding the concept-to-be negated. Note that we also trained a biLSTM which can be incorporated in [MedCAT](https://github.com/CogStack/MedCAT).
|
41 |
|
42 |
## Data
|
43 |
The pre-trained model was trained on nearly 10 million hospital notes from the Amsterdam University Medical Centres. The training data was anonymized before starting the pre-training procedure.
|