-
This project uses `pydantic
-
eds.ner_crf pipeline needs argument `window = 1` to remove CRF instead of the argument `mode = "independent"`
## Description
The mode "independent" is supposed to remove the CRF in the architect…
-
Hi,
Would you consider adding the newline character "\n" to the list of terminations (in edsnlp.pipelines.terminations)?
In a note like this:
```
pas de toux
NOVATREX
```
NOVATREX wou…
-
It seems that the eds.normalizer pipe does not act
i am using edsnlp version 0.13.1
## How to reproduce the bug
config = dict(
lowercase=True,
accents=True,
quotes=False,
…
-
As built, if the use_section=True config is applied to the eds.history pipeline, all "antécédents", "antécédents familiaux" and "histoire de la maladie" sections are used to tag entities as "history"…
-
## Score
# Description
We analysed the performance of the pipeline `eds.charlson` over 100 documents extracted from the Bordeaux CHU medical datawarehouse. We compare Charlson score extracted …
-
## How to reproduce the behaviour
Hi, it seems that the latest spacy release has bumped the numpy build dependency:
```
[build-system]
requires = [
"setuptools",
"cython>=0.25,=2…
-
## Feature type
improve
## Description
make context words before and after (different)
here : https://github.com/aphp/edsnlp/blob/master/edsnlp/utils/span_getters.py#L140
-
## Feature type
Adding a pipe to a pipeline has quite a few limitations at the moment:
```python
import edsnlp
nlp = edsnlp.blank('eds')
nlp.add_pipe('eds.matcher', config={"terms": {"key":…
-
## Feature type
Once a date has been extracted by the ML NER module (e.g., `eds.ner_crf`), it still needs to be normalized, and its format extracted to be able to shift it before replacing it in th…