tomaarsen HF staff commited on
Commit
bef30ed
1 Parent(s): 4762718

Refer users to the superior mBERT model

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -60,6 +60,8 @@ metrics:
60
 
61
  # SpanMarker for Named Entity Recognition
62
 
 
 
63
  This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for multilingual Named Entity Recognition trained on the [MultiNERD](https://huggingface.co/datasets/Babelscape/multinerd) dataset. In particular, this SpanMarker model uses [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) as the underlying encoder. See [train.py](train.py) for the training script.
64
 
65
  ## Metrics
@@ -117,6 +119,7 @@ model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-xlm-roberta-base-
117
  entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
118
  ```
119
 
 
120
 
121
  **Warning**: This model works best when punctuation is separated from the prior words, so
122
  ```python
 
60
 
61
  # SpanMarker for Named Entity Recognition
62
 
63
+ **Note**: Due to major [tokenization limitations](#Limitations), this model is deprecated in favor of the much superior [tomaarsen/span-marker-mbert-base-multinerd](https://huggingface.co/tomaarsen/span-marker-mbert-base-multinerd) model.
64
+
65
  This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for multilingual Named Entity Recognition trained on the [MultiNERD](https://huggingface.co/datasets/Babelscape/multinerd) dataset. In particular, this SpanMarker model uses [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) as the underlying encoder. See [train.py](train.py) for the training script.
66
 
67
  ## Metrics
 
119
  entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
120
  ```
121
 
122
+ ### Limitations
123
 
124
  **Warning**: This model works best when punctuation is separated from the prior words, so
125
  ```python