Add note
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that ca
|
|
| 16 |
In particular, this SpanMarker model uses [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) as the underlying encoder.
|
| 17 |
See [span_marker_verbs_train.ipynb](span_marker_verbs_train.ipynb) for the training script used to create this model.
|
| 18 |
|
|
|
|
|
|
|
| 19 |
## Usage
|
| 20 |
|
| 21 |
To use this model for inference, first install the `span_marker` library:
|
|
|
|
| 16 |
In particular, this SpanMarker model uses [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) as the underlying encoder.
|
| 17 |
See [span_marker_verbs_train.ipynb](span_marker_verbs_train.ipynb) for the training script used to create this model.
|
| 18 |
|
| 19 |
+
Note that this model is an experiment about the feasibility of SpanMarker as a POS tagger. I would generally recommend using spaCy or NLTK instead, as these are more computationally efficient approaches.
|
| 20 |
+
|
| 21 |
## Usage
|
| 22 |
|
| 23 |
To use this model for inference, first install the `span_marker` library:
|